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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    spect
    -0.08
     Hopefully
    -0.08
     hopefully
    -0.08
     الاحت
    -0.07
     мног
    -0.07
    especially
    -0.07
    ightly
    -0.07
     حفاظ
    -0.07
    _TR
    -0.07
     تج
    -0.07
    POSITIVE LOGITS
     implies
    0.10
     quantified
    0.09
    意思
    0.09
    Meaning
    0.09
    引用
    0.08
    意味着
    0.08
     meaning
    0.08
    就是说
    0.08
     referências
    0.08
    つまり
    0.08
    Act Density 0.079%

    No Known Activations