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

    Neuronpedia

    INDEX
    Explanations

    python import

    np_max-act · gemini-2.0-flash

    This neuron never fires (all activations are zero), so it isn’t detecting any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     čtyři
    -0.07
    customer
    -0.07
    icrous
    -0.07
     Lif
    -0.07
    GLfloat
    -0.06
    _PG
    -0.06
    _regex
    -0.06
     coc
    -0.06
    $self
    -0.06
     teamed
    -0.06
    POSITIVE LOGITS
    .firebase
    0.07
     подроб
    0.07
    (N
    0.06
    िश
    0.06
    (upload
    0.06
     Fluent
    0.06
    osh
    0.06
     TORT
    0.06
    (bodyParser
    0.06
    .registry
    0.06
    Act Density 0.020%

    No Known Activations