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

    Neuronpedia

    INDEX
    Explanations

    symbols and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'D
    -0.06
     Aç
    -0.06
     Таким
    -0.06
    .barDockControl
    -0.06
    (horizontal
    -0.06
    Had
    -0.06
    在
    -0.06
     Retrofit
    -0.06
     racist
    -0.06
     Lifetime
    -0.06
    POSITIVE LOGITS
     كن
    0.08
    ,:]
    0.07
    еств
    0.07
    /****************
    0.07
     dirig
    0.06
    .setBorder
    0.06
    ()]
    0.06
    OV
    0.06
    hythm
    0.06
    phins
    0.06
    Act Density 0.004%

    No Known Activations