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

    Neuronpedia

    INDEX
    Explanations

    scientific names/technical documentation

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on decimal numbers (floating-point numeric values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     precursor
    -0.06
    ูนย
    -0.06
     Approach
    -0.06
     Constant
    -0.06
    據
    -0.06
    Sand
    -0.06
     attractions
    -0.06
     arrog
    -0.06
     dedication
    -0.06
    TypeDef
    -0.06
    POSITIVE LOGITS
    uhan
    0.07
    _IL
    0.06
    lus
    0.06
     国家
    0.06
    -trigger
    0.06
    /internal
    0.06
     nuevos
    0.06
    .Alignment
    0.06
     stuffed
    0.06
    prehensive
    0.06
    Act Density 0.001%

    No Known Activations