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

    Neuronpedia

    INDEX
    Explanations

    list formatting definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    計測
    0.52
    兗
    0.49
    運び
    0.47
     ۴
    0.46
     Lauf
    0.45
     교통
    0.45
    transfected
    0.45
     attackers
    0.45
     സഹ
    0.45
    ᑉ
    0.45
    POSITIVE LOGITS
    ID
    0.53
    RO
    0.49
    Screen
    0.48
    IME
    0.47
    Architect
    0.47
    Pre
    0.47
    Que
    0.46
    Res
    0.45
    stav
    0.45
    RI
    0.45
    Act Density 0.002%

    No Known Activations