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

    Neuronpedia

    INDEX
    Explanations

    the beginning of sentences or sections

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

    after initial lowercase letters

    np_acts-logits-general · gemini-2.0-flash

    etching method, purification method

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.73
    InjectAttribute
    -0.58
     invokingState
    -0.57
     resourceCulture
    -0.55
    Vidite
    -0.55
    AddTagHelper
    -0.54
    WaitGroup
    -0.52
    Rohy
    -0.52
    Gweler
    -0.52
    jsxFileName
    -0.50
    POSITIVE LOGITS
     للمعارف
    0.58
    ougars
    0.56
    ELIN
    0.55
    媛
    0.55
    hisattva
    0.54
    berkeley
    0.54
    qrstuvwxyz
    0.54
    ctory
    0.54
    ykjav
    0.53
     birdie
    0.53
    Act Density 0.032%

    No Known Activations