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

    Neuronpedia

    INDEX
    Explanations

    math formulas

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric constants (especially floating‐point numbers) in mathematical expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    річ
    -0.08
    (mappedBy
    -0.06
    _avg
    -0.06
     přib
    -0.06
    _configuration
    -0.06
     gest
    -0.06
     Agents
    -0.06
    _agent
    -0.06
    .position
    -0.06
     trivial
    -0.06
    POSITIVE LOGITS
    extends
    0.07
     şiddet
    0.07
     приготовить
    0.07
     BILL
    0.06
    cbd
    0.06
    IRS
    0.06
    .Wh
    0.06
    >>(↵
    0.06
    ;o
    0.06
    ……………………
    0.06
    Act Density 0.009%

    No Known Activations