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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     specials
    -0.07
     首页
    -0.07
     headers
    -0.06
    -bottom
    -0.06
     να
    -0.06
     instantly
    -0.06
     jaké
    -0.06
     آمده
    -0.06
     Qur
    -0.06
     vocab
    -0.06
    POSITIVE LOGITS
    кс
    0.07
    Reduce
    0.06
    xmin
    0.06
    τια
    0.06
    undi
    0.06
    usic
    0.06
    Formatter
    0.06
    ,q
    0.06
    there
    0.06
    achat
    0.06
    Act Density 0.000%

    No Known Activations