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

    Neuronpedia

    INDEX
    Explanations

    se

    np_max-act · gemini-2.0-flash

    This neuron identifies occurrences of “pro se” (self-represented) filings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Naj
    -0.07
     Irene
    -0.06
    .Change
    -0.06
     Ryder
    -0.06
     mé
    -0.06
     fully
    -0.06
     stroj
    -0.06
     Zuk
    -0.06
     Circus
    -0.06
    glomer
    -0.06
    POSITIVE LOGITS
     strategies
    0.07
     Ре
    0.07
     encompasses
    0.07
     Detected
    0.06
     w
    0.06
    baby
    0.06
     synthes
    0.06
    猫
    0.06
     Var
    0.06
     Secrets
    0.06
    Act Density 0.001%

    No Known Activations