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

    Neuronpedia

    INDEX
    Explanations

    signal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -only
    -0.06
    _At
    -0.06
    آ
    -0.06
     dates
    -0.06
    ARM
    -0.06
     SZ
    -0.06
    рам
    -0.06
     nxt
    -0.06
     nep
    -0.06
     вариан
    -0.06
    POSITIVE LOGITS
    -HT
    0.07
     نويسنده
    0.07
     Viện
    0.07
    "indices
    0.06
    TRUE
    0.06
    CommandLine
    0.06
     onu
    0.06
    enti
    0.06
     bend
    0.06
     IPs
    0.06
    Act Density 0.068%

    No Known Activations