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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash

    The neuron responds to the placeholder “NAME_1,” i.e. occurrences of that specific character’s name.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ованих
    -0.07
     doses
    -0.07
     onTouch
    -0.07
    >({
    -0.06
    <HashMap
    -0.06
     kak
    -0.06
    욱
    -0.06
    いで
    -0.06
     galleries
    -0.06
    @AllArgsConstructor
    -0.06
    POSITIVE LOGITS
    不了
    0.07
     реги
    0.07
     마
    0.06
     confessed
    0.06
    "type
    0.06
    非
    0.06
     ending
    0.06
    "id
    0.06
     Yii
    0.06
     kia
    0.06
    Act Density 0.013%

    No Known Activations