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

    Neuronpedia

    INDEX
    Explanations

    BE

    np_max-act · gemini-2.0-flash

    This neuron responds to tokens primarily found in user-issued instructions or commands (imperative directive language).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     но
    -0.07
     MH
    -0.06
     TBD
    -0.06
    eş
    -0.06
    MH
    -0.06
    gf
    -0.06
    RAM
    -0.06
    ampp
    -0.06
    chg
    -0.06
    ---------↵↵
    -0.06
    POSITIVE LOGITS
     Situation
    0.07
     denote
    0.07
     Survey
    0.07
    .Deserialize
    0.07
     statusCode
    0.06
     nome
    0.06
    rypt
    0.06
    placer
    0.06
    <?>
    0.06
     bigotry
    0.06
    Act Density 0.026%

    No Known Activations