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

    Neuronpedia

    INDEX
    Explanations

    black

    np_max-act · gemini-2.0-flash

    the word “black” when referring to race or African‐American identity.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Defs
    -0.07
    .Expressions
    -0.07
     Nan
    -0.07
     guitarist
    -0.07
    路
    -0.07
     även
    -0.07
     pregunta
    -0.07
     Prophet
    -0.06
     Cash
    -0.06
    ush
    -0.06
    POSITIVE LOGITS
     black
    0.08
     shake
    0.07
     Black
    0.07
     chunks
    0.07
     黑
    0.07
     enorm
    0.06
     ())
    0.06
    black
    0.06
    .".
    0.06
     premature
    0.06
    Act Density 0.010%

    No Known Activations