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

    Neuronpedia

    INDEX
    Explanations

    short note

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sidelines
    0.44
     AIP
    0.42
    사회
    0.41
    жли
    0.39
    $
    0.38
    <0x9A>
    0.38
    тали
    0.37
    '$,
    0.37
    ellations
    0.36
    근
    0.36
    POSITIVE LOGITS
    ഡിയോ
    0.55
     výraz
    0.55
     bestaat
    0.53
     besteht
    0.52
    nosi
    0.52
     giocatore
    0.52
     zák
    0.51
     geeft
    0.51
    ępu
    0.49
     vakar
    0.48
    Act Density 0.038%

    No Known Activations