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

    Neuronpedia

    INDEX
    Explanations

    apply

    np_max-act · gemini-2.0-flash

    The neuron detects Spanish imperative‐mood verbs used to give instructions (e.g., “Utiliza,” “Aplica,” “Usa”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _idx
    -0.07
     platform
    -0.07
     religions
    -0.06
    Class
    -0.06
     paradigm
    -0.06
    FU
    -0.06
     McGregor
    -0.06
     explains
    -0.06
    .push
    -0.06
    mayacak
    -0.06
    POSITIVE LOGITS
     Bew
    0.06
    ความค
    0.06
    投注
    0.06
    、この
    0.06
    Ậ
    0.06
    谱
    0.06
    .Ultra
    0.06
    Lib
    0.06
    บล
    0.06
     Applies
    0.06
    Act Density 0.011%

    No Known Activations