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

    Neuronpedia

    INDEX
    Explanations

    (*

    np_max-act · gemini-2.0-flash

    The neuron is effectively dead—it does not activate on any tokens and thus matches no particular pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Vision
    -0.07
    hot
    -0.06
    icular
    -0.06
     promoter
    -0.06
    itudes
    -0.06
    rench
    -0.06
     deeds
    -0.06
    Injection
    -0.06
    .expression
    -0.06
    scientific
    -0.06
    POSITIVE LOGITS
     trai
    0.06
     دوباره
    0.06
    ("\
    0.06
    _CAST
    0.06
     *@
    0.06
     refunded
    0.06
     Taco
    0.06
     Alternate
    0.06
     rapidement
    0.06
    人民共和国
    0.06
    Act Density 0.000%

    No Known Activations