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

    Neuronpedia

    INDEX
    Explanations

    questions and topics

    np_acts-logits-general · gemini-2.5-flash-lite

    `If`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     on
    1.33
     I
    0.91
     with
    0.84
    dengan
    0.83
     детали
    0.82
    ድግዳ
    0.82
     地
    0.79
     onPress
    0.78
     onscreen
    0.78
    作った
    0.78
    POSITIVE LOGITS
    u
    1.84
    er
    1.77
    ar
    1.59
    ap
    1.58
    ла
    1.54
    ı
    1.48
    ون
    1.45
    an
    1.44
    ب
    1.38
    ர்
    1.34
    Act Density 0.861%

    No Known Activations