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

    Neuronpedia

    INDEX
    Explanations

    any

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on floating‐point numerical tokens (decimal numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    انگ
    -0.07
    丽
    -0.07
    ان
    -0.07
    .Dispatcher
    -0.06
     UIL
    -0.06
     safari
    -0.06
    ums
    -0.06
     mafia
    -0.06
    kiego
    -0.06
    izia
    -0.06
    POSITIVE LOGITS
    оваться
    0.07
     και
    0.07
    StoryboardSegue
    0.06
    _bits
    0.06
    55
    0.06
     stumbled
    0.06
     complaining
    0.06
     minY
    0.06
     Соб
    0.06
     broadcasting
    0.06
    Act Density 0.000%

    No Known Activations