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

    Neuronpedia

    INDEX
    Explanations

    all of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ۶
    0.67
     skyrocketing
    0.64
     GoObject
    0.63
    ❽
    0.62
     मद्देन
    0.61
     JP
    0.59
    యర్
    0.59
     வருகிறது
    0.58
     對
    0.58
     DJI
    0.58
    POSITIVE LOGITS
     and
    1.04
     of
    0.98
    وا
    0.94
     in
    0.91
    ين
    0.86
    بر
    0.86
    س
    0.84
    г
    0.82
     with
    0.80
    2
    0.80
    Act Density 0.000%

    No Known Activations