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

    Neuronpedia

    INDEX
    Explanations

    groupId closing tag

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     of
    0.82
     at
    0.79
    of
    0.78
     by
    0.75
     on
    0.73
     {
    0.68
    ?
    0.58
    ozer
    0.57
    iale
    0.56
    리
    0.56
    POSITIVE LOGITS
    ی
    0.97
    も
    0.85
    ש
    0.84
    т
    0.82
    ের
    0.80
    もら
    0.79
     что
    0.77
    在
    0.77
    ও
    0.76
    ி
    0.75
    Act Density 0.000%

    No Known Activations