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

    Neuronpedia

    INDEX
    Explanations

    quotes in news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _return
    -0.06
    _strip
    -0.06
     creep
    -0.06
    /twitter
    -0.06
     confession
    -0.06
     part
    -0.06
    ças
    -0.05
     Apartment
    -0.05
    entric
    -0.05
     critically
    -0.05
    POSITIVE LOGITS
     Bod
    0.07
    egasus
    0.07
    ghest
    0.07
    Alan
    0.07
    .over
    0.06
     UNIX
    0.06
    aptops
    0.06
    茨
    0.06
    (jLabel
    0.06
     surg
    0.06
    Act Density 0.017%

    No Known Activations