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

    Neuronpedia

    INDEX
    Explanations

    unw

    np_max-act · gemini-2.0-flash

    say "word endings"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Negative Logits
     Dun
    -0.60
     dun
    -0.60
    Dun
    -0.59
    quil
    -0.58
    matched
    -0.54
    Ghi
    -0.54
    tell
    -0.54
    antd
    -0.52
    esta
    -0.51
    Collegamenti
    -0.51
    POSITIVE LOGITS
    UserScript
    0.66
    󠁢
    0.66
    RenderAtEndOf
    0.63
     فريبيس
    0.63
    uxxxx
    0.63
    HomeAsUpEnabled
    0.62
    featureID
    0.61
    principalColumn
    0.60
    s
    0.57
     تضيفلها
    0.56
    Act Density 0.290%

    No Known Activations