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

    Neuronpedia

    INDEX
    Explanations

    question marks

    np_max-act · gemini-2.0-flash

    This neuron responds to special sequence‐boundary tokens (e.g. end‐of‐turn or end‐of‐text markers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     عشق
    -0.06
    (sys
    -0.06
    计划
    -0.06
    Bush
    -0.06
     Zac
    -0.06
     Mercy
    -0.06
    縮
    -0.06
     Asians
    -0.06
     下午
    -0.06
     همیشه
    -0.06
    POSITIVE LOGITS
    .espresso
    0.07
     vide
    0.06
     optimizations
    0.06
    募
    0.06
     unknow
    0.06
     totaling
    0.06
    웨어
    0.06
    grave
    0.06
     sca
    0.06
    .he
    0.06
    Act Density 0.050%

    No Known Activations