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

    Neuronpedia

    INDEX
    Explanations

    the code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     está
    0.46
     reason
    0.45
    其他
    0.45
     காரணம்
    0.45
    写真は
    0.45
     soothing
    0.44
     másik
    0.44
    氣
    0.44
     other
    0.43
     underlying
    0.43
    POSITIVE LOGITS
     valamint
    0.46
     berikut
    0.46
    FBSDKInternal
    0.45
    roke
    0.45
    LoopBlend
    0.44
    amasını
    0.44
     potranno
    0.43
     살펴보도록
    0.43
     folgenden
    0.43
    masını
    0.43
    Act Density 0.080%

    No Known Activations