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

    Neuronpedia

    INDEX
    Explanations

    Brain research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :path
    -0.07
    tbl
    -0.07
     shepherd
    -0.07
     Schultz
    -0.07
    (original
    -0.06
     commodities
    -0.06
    	valid
    -0.06
     glob
    -0.06
    benchmark
    -0.06
    year
    -0.06
    POSITIVE LOGITS
    .engine
    0.07
    .prof
    0.06
    .msg
    0.06
    _sr
    0.06
     S
    0.06
     surrogate
    0.06
     slik
    0.06
    AUTH
    0.06
     ashamed
    0.06
     eş
    0.06
    Act Density 0.049%

    No Known Activations