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

    Neuronpedia

    INDEX
    Explanations

    special characters and symbols in mathematical or programming contexts

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

    technical terms and markup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \{\\
    -0.37
    ագրություններ
    -0.33
    kusen
    -0.33
    calaure
    -0.32
     didik
    -0.31
     informacija
    -0.31
     dimaksud
    -0.30
     Sieger
    -0.30
     atve
    -0.30
    ConverterFactory
    -0.29
    POSITIVE LOGITS
     FetchType
    0.57
    adpleegd
    0.54
    ⏟
    0.51
    niſſe
    0.49
     Bolo
    0.48
    BibitemShut
    0.48
    WriteTagHelper
    0.47
     partial
    0.46
    ]")]
    0.45
     мәкал
    0.45
    Act Density 0.348%

    No Known Activations