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

    Neuronpedia

    INDEX
    Explanations

    Actions or financial transactions

    np_max-act · gemini-2.0-flash

    The neuron detects third-person singular present-tense verbs ending in “s.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     yourself
    -0.08
     dancer
    -0.07
    Consumer
    -0.06
     Everybody
    -0.06
     che
    -0.06
     you
    -0.06
    Once
    -0.06
     character
    -0.06
     breast
    -0.06
     purch
    -0.06
    POSITIVE LOGITS
    ks
    0.10
    s
    0.10
    İS
    0.09
    DS
    0.09
    GS
    0.09
    kas
    0.09
    aks
    0.09
    KS
    0.09
    bas
    0.09
    \s
    0.09
    Act Density 0.641%

    No Known Activations