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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rotating
    -0.07
    Из
    -0.06
     Dry
    -0.06
     practice
    -0.06
    iri
    -0.06
    inis
    -0.06
     incl
    -0.06
     paris
    -0.06
     judged
    -0.06
     propName
    -0.06
    POSITIVE LOGITS
    его
    0.07
     define
    0.07
    웅
    0.06
     sexuales
    0.06
    ؤال
    0.06
    ubits
    0.06
     cath
    0.06
    animations
    0.06
    IVAL
    0.06
    astreet
    0.06
    Act Density 0.019%

    No Known Activations