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

    Neuronpedia

    INDEX
    Explanations

    say "implify"

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
     Dub
    -0.07
     Lod
    -0.07
     lungs
    -0.07
    /↵↵↵
    -0.07
    ifting
    -0.07
    太快
    -0.07
     sở
    -0.07
     weather
    -0.07
     strugg
    -0.07
    ugging
    -0.07
    POSITIVE LOGITS
    פוט
    0.07
     activations
    0.07
    _Err
    0.07
    _ENT
    0.07
     acquitted
    0.07
     qreal
    0.06
    三千
    0.06
    媳
    0.06
    뷔
    0.06
     QPushButton
    0.06
    Act Density 0.008%

    No Known Activations