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

    Neuronpedia

    INDEX
    Explanations

    sequence 74

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sweep
    0.77
     transcend
    0.76
     plunger
    0.73
     sounding
    0.70
     devenir
    0.69
    쌓
    0.69
     फट
    0.67
     outperformed
    0.66
    ザ
    0.66
     engulfed
    0.65
    POSITIVE LOGITS
     wp
    0.71
    uiden
    0.70
    awai
    0.67
    ilerin
    0.67
     силу
    0.66
     grubu
    0.64
    itab
    0.64
    際に
    0.64
    arik
    0.64
    rein
    0.63
    Act Density 0.079%

    No Known Activations