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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NOTICE
    -0.08
     communism
    -0.07
     variability
    -0.06
     valley
    -0.06
     terrorism
    -0.06
     OSX
    -0.06
    System
    -0.06
    rapy
    -0.06
    .ident
    -0.06
    experience
    -0.06
    POSITIVE LOGITS
     لت
    0.07
    äll
    0.06
    ophobic
    0.06
    lagen
    0.06
     都
    0.06
    amiliar
    0.06
     Clown
    0.06
     Μαρ
    0.06
    ables
    0.06
    561
    0.06
    Act Density 0.006%

    No Known Activations