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

    Neuronpedia

    INDEX
    Explanations

    flags and symbols

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on numerical tokens (e.g. years, centuries, and other numeral-based references).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Invariant
    -0.07
    itest
    -0.06
     Operator
    -0.06
    搬
    -0.06
     ecology
    -0.06
    esco
    -0.06
    Hide
    -0.06
     seize
    -0.06
    Execute
    -0.06
    았다
    -0.06
    POSITIVE LOGITS
    'LBL
    0.07
    (resp
    0.06
    カテ
    0.06
     otel
    0.06
     потрап
    0.06
    	Returns
    0.06
     ure
    0.06
     jLabel
    0.06
     投稿
    0.06
    .showToast
    0.06
    Act Density 0.019%

    No Known Activations