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

    Neuronpedia

    INDEX
    Explanations

    assertions/tests

    np_max-act · gemini-2.0-flash

    This neuron detects floating-point numeric literals (numbers containing a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Butter
    -0.07
    _af
    -0.07
    ”
    -0.06
    tember
    -0.06
    <KeyValuePair
    -0.06
     detective
    -0.06
    ITAL
    -0.06
    _Description
    -0.06
    cross
    -0.06
     showAlert
    -0.06
    POSITIVE LOGITS
     capsules
    0.07
    적으로
    0.07
     />↵
    0.06
     успеш
    0.06
     hollow
    0.06
     була
    0.06
    (stypy
    0.06
    /pass
    0.06
    _pix
    0.06
    [string
    0.06
    Act Density 0.007%

    No Known Activations