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

    Neuronpedia

    INDEX
    Explanations

    special tokens or symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     další
    1.58
     relación
    1.53
     destacó
    1.52
     coût
    1.48
     creatividad
    1.44
    Nick
    1.43
     Tidak
    1.42
     lainnya
    1.42
     ďal
    1.41
     sosok
    1.40
    POSITIVE LOGITS
     solidly
    0.82
     unnecessarily
    0.80
     appropriate
    0.78
     horribly
    0.77
     over
    0.76
     overs
    0.75
    pots
    0.75
     inappropriately
    0.74
     indiscrimin
    0.73
    tied
    0.73
    Act Density 0.007%

    No Known Activations