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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron primarily responds to standalone numeric tokens (e.g. line numbers and other isolated digits).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     باشید
    -0.08
    cido
    -0.07
    <data
    -0.07
    _edit
    -0.07
    .media
    -0.07
     tersebut
    -0.06
    -details
    -0.06
    blr
    -0.06
     faithfully
    -0.06
     Ages
    -0.06
    POSITIVE LOGITS
     Manufact
    0.08
     dez
    0.07
     Зап
    0.07
     ER
    0.07
     ROT
    0.07
     Autos
    0.06
     essay
    0.06
     diagnostic
    0.06
    ถนน
    0.06
     crem
    0.06
    Act Density 0.001%

    No Known Activations