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

    Neuronpedia

    INDEX
    Explanations

    Code/Math/Disclaimer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Slo
    -0.07
     aşırı
    -0.06
     ممن
    -0.06
    <ll
    -0.06
    ��
    -0.06
    ็นส
    -0.06
     इत
    -0.06
     ülke
    -0.06
     rencont
    -0.06
     cũng
    -0.06
    POSITIVE LOGITS
     employment
    0.08
     hunters
    0.07
     abandon
    0.07
    BIND
    0.07
     excluded
    0.06
     CharSet
    0.06
    :NO
    0.06
    /browser
    0.06
    roys
    0.06
    اري
    0.06
    Act Density 0.000%

    No Known Activations