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

    Neuronpedia

    INDEX
    Explanations

    software code and licenses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    institution
    -0.07
     rugged
    -0.06
    bate
    -0.06
    stories
    -0.06
    ematics
    -0.06
    ickými
    -0.06
    -str
    -0.06
     fora
    -0.06
    layer
    -0.06
     visions
    -0.06
    POSITIVE LOGITS
     fours
    0.06
    Symbols
    0.06
     grupo
    0.06
     CultureInfo
    0.06
     gboolean
    0.06
     CSP
    0.06
    ắc
    0.06
     skim
    0.06
     sph
    0.06
     розк
    0.06
    Act Density 0.012%

    No Known Activations