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

    Neuronpedia

    INDEX
    Explanations

    Issues to be addressed

    np_max-act · gemini-2.0-flash

    The neuron fires on language expressing recommendations or requirements (e.g. “should,” “must,” “addressed”), i.e. prescription/call-to-action phrasing.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ADMIN
    -0.07
    ectors
    -0.07
    INTEGER
    -0.06
    Stats
    -0.06
    .parentElement
    -0.06
    ogan
    -0.06
    \Image
    -0.06
     FileUtils
    -0.06
     Afghan
    -0.06
    _IMPL
    -0.06
    POSITIVE LOGITS
     gider
    0.06
     bub
    0.06
     фун
    0.06
     Paula
    0.06
    �
    0.06
     руб
    0.06
     처리
    0.06
    _legend
    0.06
     comida
    0.06
     yup
    0.06
    Act Density 0.035%

    No Known Activations