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

    Neuronpedia

    INDEX
    Explanations

    comma separated lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wave
    0.64
     Layer
    0.64
     H
    0.62
     induced
    0.62
     Mu
    0.62
     Induced
    0.62
     R
    0.61
     C
    0.59
     J
    0.58
     Rate
    0.57
    POSITIVE LOGITS
     અથવા
    1.02
     또는
    0.98
     లేదా
    0.98
     அல்லது
    0.95
     ಅಥವಾ
    0.95
     hoặc
    0.93
    रीबन
    0.92
    または
    0.90
    もしくは
    0.89
     または
    0.87
    Act Density 0.227%

    No Known Activations