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

    Neuronpedia

    INDEX
    Explanations

    URLs and random characters

    np_max-act · gemini-2.0-flash

    The neuron is primarily triggered by numeric tokens, i.e. digits and numbers embedded in text (such as timestamps, IDs, dimensions, and other digit sequences).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     thieves
    -0.07
     NATIONAL
    -0.07
     Average
    -0.06
    Provides
    -0.06
    ING
    -0.06
    (join
    -0.06
     Fern
    -0.06
    <Test
    -0.06
     Finch
    -0.06
     vaguely
    -0.06
    POSITIVE LOGITS
     banc
    0.06
    wrapped
    0.06
     쪽지
    0.06
     sonraki
    0.06
    idebar
    0.06
    CW
    0.06
    apollo
    0.06
    pekt
    0.06
    .co
    0.06
    ています
    0.06
    Act Density 0.035%

    No Known Activations