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

    Neuronpedia

    INDEX
    Explanations

    35

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     riot
    -0.08
     assertion
    -0.08
    局
    -0.08
    Article
    -0.08
     Get
    -0.07
     official
    -0.07
     dan
    -0.07
     advisory
    -0.07
     Update
    -0.07
    responseObject
    -0.07
    POSITIVE LOGITS
    MF
    0.08
    .mkdirs
    0.07
    leness
    0.06
    تي
    0.06
    '^$',
    0.06
     Silk
    0.06
    .maxcdn
    0.06
     guts
    0.06
    .hl
    0.06
    teg
    0.06
    Act Density 0.112%

    No Known Activations