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

    Neuronpedia

    INDEX
    Explanations

    task

    np_max-act · gemini-2.0-flash

    This neuron remains inactive (all activation values are zero) and thus does not detect any pattern—i.e. it’s a “dead” neuron.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    智
    -0.07
     incontro
    -0.07
     vou
    -0.06
     inşa
    -0.06
     autonom
    -0.06
    $pdf
    -0.06
     drowned
    -0.06
    isms
    -0.06
    (plugin
    -0.06
    �어
    -0.06
    POSITIVE LOGITS
     treasury
    0.06
    .site
    0.06
    )↵↵↵↵↵
    0.06
    خصص
    0.06
     versa
    0.06
    _SPACE
    0.06
     season
    0.06
    一页
    0.06
     claim
    0.06
     مشخص
    0.06
    Act Density 0.050%

    No Known Activations