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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron activates on floating-point numeric literals (numbers containing a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    stime
    -0.08
    _TARGET
    -0.07
     ак
    -0.07
    Location
    -0.06
     Work
    -0.06
    .Loader
    -0.06
    peech
    -0.06
    expr
    -0.06
    .weather
    -0.06
    oogle
    -0.06
    POSITIVE LOGITS
    stva
    0.07
    iture
    0.06
    口
    0.06
    ¿
    0.06
     niż
    0.06
     (!$
    0.06
     ー
    0.06
     hog
    0.06
    으며
    0.06
     sistemi
    0.05
    Act Density 0.014%

    No Known Activations