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

    Neuronpedia

    INDEX
    Explanations

    asterisk/parenthesis

    np_max-act · gemini-2.0-flash

    The neuron is attuned to mathematical exponentiation notation, especially the “**” operator and its surrounding power‐of expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _saida
    -0.07
    Vue
    -0.07
     rodi
    -0.07
     satisfy
    -0.06
     vibr
    -0.06
    벌
    -0.06
    Whole
    -0.06
     sunset
    -0.06
    謝
    -0.06
     Eleanor
    -0.06
    POSITIVE LOGITS
     mesmo
    0.06
    DispatchToProps
    0.06
     kred
    0.06
    buckets
    0.06
     bcrypt
    0.06
    иты
    0.06
     Marxist
    0.06
    ixel
    0.06
    ideo
    0.06
     robust
    0.06
    Act Density 0.008%

    No Known Activations