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

    Neuronpedia

    INDEX
    Explanations

    crisis hotlines and phone numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    1.18
     at
    1.07
    to
    1.05
    ly
    1.03
    2
    1.02
    that
    0.97
    from
    0.96
    ă
    0.93
     of
    0.93
     for
    0.91
    POSITIVE LOGITS
    ில்
    0.84
    ৭
    0.84
    ოს
    0.79
     transpos
    0.78
    тике
    0.77
    िशन
    0.76
    ти
    0.75
    िटेशन
    0.75
    ри
    0.74
     revoc
    0.74
    Act Density 0.002%

    No Known Activations