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

    Neuronpedia

    INDEX
    Explanations

    Codes or names

    np_max-act · gemini-2.0-flash

    This neuron fires on placeholder name tokens (e.g. “NAME_1,” “NAME_2,” “NAME_3,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Cooling
    -0.07
     kidneys
    -0.07
    Fort
    -0.07
     Sh
    -0.07
    šení
    -0.07
    /components
    -0.07
    lení
    -0.06
     retrieval
    -0.06
     tolerant
    -0.06
    열
    -0.06
    POSITIVE LOGITS
    ouz
    0.06
    learn
    0.06
     Там
    0.06
    Authors
    0.06
    ori
    0.06
     двух
    0.06
     přitom
    0.06
    ,callback
    0.06
     преж
    0.06
    .char
    0.06
    Act Density 0.044%

    No Known Activations