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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash

    The neuron detects numerical tokens, especially measurements or decimal numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	R
    -0.07
    ･
    -0.06
    iche
    -0.06
     lint
    -0.06
    ,result
    -0.06
     parse
    -0.06
    iques
    -0.06
    uro
    -0.06
    jid
    -0.06
    chema
    -0.06
    POSITIVE LOGITS
    ความค
    0.07
     at
    0.07
     exhilar
    0.06
     cổ
    0.06
    .removeClass
    0.06
     Savannah
    0.06
    .FromSeconds
    0.06
     mAdapter
    0.06
     답변
    0.06
     kamu
    0.06
    Act Density 0.043%

    No Known Activations