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

    Neuronpedia

    INDEX
    Explanations

    odds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     віль
    -0.08
     पड़
    -0.07
    lý
    -0.07
    اوي
    -0.07
    _review
    -0.07
    _RM
    -0.07
     Augusta
    -0.07
     bilingual
    -0.06
     Něm
    -0.06
    /member
    -0.06
    POSITIVE LOGITS
     odds
    0.16
     Odds
    0.11
    (#
    0.07
     Evans
    0.06
    mid
    0.06
    Hours
    0.06
     مت
    0.06
    .eth
    0.06
    _digest
    0.06
     weird
    0.06
    Act Density 0.003%

    No Known Activations