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

    Neuronpedia

    INDEX
    Explanations

    Historical periods

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens that are parts of year or date references.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     пласти
    -0.07
     onemoc
    -0.06
     �
    -0.06
    /fl
    -0.06
     UX
    -0.06
     paycheck
    -0.06
    wner
    -0.06
     slightest
    -0.06
    \Mapping
    -0.06
    (($
    -0.06
    POSITIVE LOGITS
     Gather
    0.08
    Trademark
    0.07
     nike
    0.06
    ؤال
    0.06
     osób
    0.06
    .break
    0.06
    ，此
    0.06
     rejo
    0.06
     DataContext
    0.06
     y
    0.06
    Act Density 0.015%

    No Known Activations