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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    The neuron is detecting the occurrence of the preposition “for,” especially when it appears in user requests for suggestions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    isode
    -0.07
    urgent
    -0.07
    สะ
    -0.06
     transmit
    -0.06
    tat
    -0.06
    роме
    -0.06
    Enviar
    -0.06
     by
    -0.06
     drink
    -0.06
     Yani
    -0.06
    POSITIVE LOGITS
     catalogs
    0.07
    การส
    0.06
     шп
    0.06
    leting
    0.06
    sat
    0.06
    Comparison
    0.06
     {//
    0.06
     stringstream
    0.06
    Pick
    0.06
     برای
    0.06
    Act Density 0.043%

    No Known Activations