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

    Neuronpedia

    INDEX
    Explanations

    `[Tooltip]` descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +%
    0.36
    ఖా
    0.34
    anay
    0.29
    felt
    0.29
    转型
    0.29
    ătur
    0.28
    ,"+
    0.28
    帧
    0.28
    an
    0.28
    arakat
    0.28
    POSITIVE LOGITS
    This
    0.41
     This
    0.40
    The
    0.38
     The
    0.35
     Debye
    0.34
     neither
    0.34
     excludes
    0.33
    excluding
    0.33
    این
    0.33
     equating
    0.33
    Act Density 0.000%

    No Known Activations