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

    Neuronpedia

    INDEX
    Explanations

    giving advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    659
    -0.07
    IFO
    -0.06
    ुख
    -0.06
    ClientId
    -0.06
    ・・・
    -0.06
    CI
    -0.06
    IP
    -0.06
    Hour
    -0.06
     jeu
    -0.06
     CONTENT
    -0.06
    POSITIVE LOGITS
    responseObject
    0.07
    енью
    0.06
     rapes
    0.06
     Abu
    0.06
     ///↵
    0.06
     -/↵
    0.06
    entially
    0.06
     nasıl
    0.06
    inspace
    0.06
     capit
    0.06
    Act Density 0.112%

    No Known Activations