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

    Neuronpedia

    INDEX
    Explanations

    Careers and time periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    edula
    -0.07
    ReLU
    -0.07
     XSS
    -0.06
     ε�
    -0.06
     Wikispecies
    -0.06
    менш
    -0.06
     Lilly
    -0.06
    夫
    -0.06
     مثال
    -0.06
     desta
    -0.06
    POSITIVE LOGITS
    (B
    0.07
    (first
    0.07
    isp
    0.07
     descendants
    0.06
    929
    0.06
    jang
    0.06
    US
    0.06
    //--
    0.06
    (pk
    0.06
    ,''
    0.06
    Act Density 0.043%

    No Known Activations