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

    Neuronpedia

    INDEX
    Explanations

    distinctive or essential features related to technology or resources

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

    Code, math, or uncommon words

    np_acts-logits-general · gemini-2.0-flash

    end of sentence or clause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vPvB
    -0.67
    ſelf
    -0.64
     crdi
    -0.63
    Rohy
    -0.61
     betweenstory
    -0.61
     iconFacebook
    -0.58
    WritableDatabase
    -0.58
    ItemBackground
    -0.58
    ſelves
    -0.57
     муніципалі
    -0.56
    POSITIVE LOGITS
    complexContent
    0.63
    ↵
    0.61
    pture
    0.56
    :✨
    0.53
    uxxxx
    0.53
    ряд
    0.53
    inį
    0.52
    MemoryWarning
    0.52
     وتسجيلات
    0.50
     narkoba
    0.49
    Act Density 0.066%

    No Known Activations