Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    sections of text with no activations, indicating it is inactive or not detecting any specific content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens after periods and common words

    np_acts-logits-general · gemini-2.0-flash

    legal context and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الحره
    -0.80
     invokingState
    -0.70
     виправивши
    -0.67
    tagHelperRunner
    -0.66
    PreferredItem
    -0.66
     tartalomajánló
    -0.66
    #+#
    -0.65
     transfieras
    -0.65
    mybatisplus
    -0.64
     TimeUnit
    -0.62
    POSITIVE LOGITS
    исленность
    0.56
    searching
    0.51
     limone
    0.48
    引用
    0.45
    śli
    0.45
    зулта
    0.43
    zzleHttp
    0.43
    RequestQueue
    0.43
    Shutter
    0.42
     cảnh
    0.42
    Act Density 0.062%

    No Known Activations