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

    Neuronpedia

    INDEX
    Explanations

    api

    np_max-act · gemini-2.0-flash

    The neuron activates on segments of fully-qualified identifiers (dotted package/class names) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ้ใน
    -0.07
     recalls
    -0.07
    Become
    -0.06
    _DEPEND
    -0.06
    _loss
    -0.06
     loses
    -0.06
     bef
    -0.06
     informações
    -0.06
     SMB
    -0.06
    _REPORT
    -0.06
    POSITIVE LOGITS
     cerebral
    0.07
     HttpNotFound
    0.07
    oined
    0.07
     Invocation
    0.07
    *w
    0.06
    getPage
    0.06
    玉
    0.06
    .getUserId
    0.06
     浙江
    0.06
    !!");↵
    0.06
    Act Density 0.048%

    No Known Activations