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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash

    This neuron activates on four-digit numeric tokens representing years or dates.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     childish
    -0.06
    履
    -0.06
     Abe
    -0.06
     tornado
    -0.06
     Dayton
    -0.06
     Interior
    -0.06
    ButtonItem
    -0.06
    _padding
    -0.06
     Sites
    -0.06
     玩
    -0.06
    POSITIVE LOGITS
    ..."
    0.07
    ijkl
    0.07
     degradation
    0.07
     contraction
    0.06
    astos
    0.06
    “So
    0.06
     disgr
    0.06
     prostřed
    0.06
    /user
    0.06
    чил
    0.06
    Act Density 0.077%

    No Known Activations