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

    Neuronpedia

    INDEX
    Explanations

    exclamatory oh god/gosh

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ス
    0.81
    u
    0.69
     in
    0.67
    ও
    0.66
     murder
    0.65
    も
    0.63
    d
    0.63
     inconsider
    0.63
    s
    0.61
    在
    0.60
    POSITIVE LOGITS
    at
    0.81
    ك
    0.71
    for
    0.70
    isem
    0.67
    ર
    0.66
    ва
    0.65
    را
    0.65
     for
    0.64
    م
    0.63
    र्निंग
    0.62
    Act Density 0.000%

    No Known Activations