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

    Neuronpedia

    INDEX
    Explanations

    the Data Analysis Toolpak

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     패턴
    0.58
    㓦
    0.58
    雰
    0.57
    됩니다
    0.55
    gateTime
    0.55
     მხოლოდ
    0.54
     테이블
    0.54
    ທາງ
    0.53
     парла
    0.52
     ಕಂಚ
    0.51
    POSITIVE LOGITS
    la
    0.68
    i
    0.63
    '
    0.59
    ai
    0.54
    lo
    0.53
    ink
    0.53
    ah
    0.52
    ,
    0.51
    he
    0.50
    zk
    0.50
    Act Density 0.001%

    No Known Activations