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

    Neuronpedia

    INDEX
    Explanations

    citations

    np_max-act · gemini-2.0-flash

    This neuron responds to numeric tokens (numbers such as page/volume figures and years).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .ui
    -0.07
     rozum
    -0.07
     kings
    -0.07
    _I
    -0.07
    .useState
    -0.07
    .c
    -0.07
     guidelines
    -0.07
     ruling
    -0.07
     trivia
    -0.07
     implied
    -0.07
    POSITIVE LOGITS
    30
    0.10
    170
    0.10
    20
    0.10
    40
    0.10
    110
    0.09
    80
    0.09
    50
    0.09
    590
    0.09
    70
    0.09
    580
    0.08
    Act Density 0.298%

    No Known Activations