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

    Neuronpedia

    INDEX
    Explanations

    Dates

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens that are part of date and time expressions (e.g., months, days, and times).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Configuration
    -0.07
    (encoding
    -0.07
    /Login
    -0.07
    Span
    -0.07
    Radius
    -0.07
     skiing
    -0.06
    Seg
    -0.06
    Manufact
    -0.06
    @NgModule
    -0.06
     Gundam
    -0.06
    POSITIVE LOGITS
     Finds
    0.07
    izzy
    0.07
     alien
    0.07
    _pi
    0.07
    PCI
    0.06
     bergen
    0.06
    erea
    0.06
     Number
    0.06
     الإ
    0.06
    *)((
    0.06
    Act Density 0.032%

    No Known Activations