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

    Neuronpedia

    INDEX
    Explanations

    v

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     самостоя
    -0.07
    Callback
    -0.06
    Gene
    -0.06
    _COOKIE
    -0.06
    쐬
    -0.06
    (pub
    -0.06
    _CHIP
    -0.06
     preprocessing
    -0.06
     sank
    -0.06
    渐
    -0.06
    POSITIVE LOGITS
    ༻
    0.07
    十七条
    0.07
    Errors
    0.07
     gonna
    0.07
    穗
    0.07
    찌
    0.07
    ῑ
    0.07
     could
    0.07
     billboard
    0.07
    upo
    0.07
    Act Density 0.001%

    No Known Activations