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

    Neuronpedia

    INDEX
    Explanations

    Dates and times

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric components of dates and times (e.g. day, month, year, hour, minute, second) in timestamp‐style strings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Russians
    -0.07
    chi
    -0.07
    RoleId
    -0.06
    bx
    -0.06
     Assert
    -0.06
    _op
    -0.06
    책
    -0.06
     kne
    -0.06
     director
    -0.06
    Velocity
    -0.06
    POSITIVE LOGITS
    adf
    0.06
     abre
    0.06
    ("/{
    0.06
     sami
    0.06
    §Ã
    0.06
    /plain
    0.06
    BACKGROUND
    0.06
     hypothesis
    0.06
     stav
    0.06
     виступ
    0.06
    Act Density 0.013%

    No Known Activations