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

    Neuronpedia

    INDEX
    Explanations

    mocking programming concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    e
    1.16
    h
    0.91
     decency
    0.88
     segu
    0.88
     She
    0.83
    yi
    0.83
     nood
    0.82
     Pare
    0.82
     Clear
    0.81
     느
    0.81
    POSITIVE LOGITS
    िटेशन
    0.99
    ীর
    0.89
    టువంటి
    0.87
    िएशन
    0.86
    ु
    0.84
    দের
    0.82
     Расійскай
    0.82
     Ελλά
    0.82
     هەر
    0.82
     Escrit
    0.81
    Act Density 0.003%

    No Known Activations