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

    Neuronpedia

    INDEX
    Explanations

    genetic code or Transformer Encoder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     epinephrine
    1.10
     mils
    1.02
    ަމ
    0.96
    盐
    0.95
    ᾧ
    0.95
    bolo
    0.95
    ையாள
    0.95
    ագ
    0.93
    nette
    0.93
     unacceptable
    0.93
    POSITIVE LOGITS
    t
    0.98
    Innovation
    0.97
    &
    0.91
    Seeking
    0.88
    Location
    0.86
    Complete
    0.86
    頃
    0.85
    Sequence
    0.85
    tim
    0.84
    完成
    0.83
    Act Density 0.001%

    No Known Activations