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

    Neuronpedia

    INDEX
    Explanations

    listing function arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     opera
    0.40
     ಸಾ
    0.40
     குற
    0.40
     drog
    0.38
    Opera
    0.38
    眉
    0.38
     collision
    0.38
     congru
    0.37
     حافظ
    0.37
     Hyper
    0.36
    POSITIVE LOGITS
    Dispatch
    0.39
     Vy
    0.39
     Wayne
    0.39
    VY
    0.36
     Victor
    0.36
    Yb
    0.35
    VW
    0.35
     ويم
    0.35
    WC
    0.34
    jst
    0.34
    Act Density 0.013%

    No Known Activations