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

    Neuronpedia

    INDEX
    Explanations

    Windows character encoding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     preventive
    -0.08
     cuidado
    -0.07
     care
    -0.07
    .Predicate
    -0.07
     preventative
    -0.07
    .Height
    -0.07
     record
    -0.07
    ('</
    -0.07
     মাত্র
    -0.07
    Executive
    -0.07
    POSITIVE LOGITS
     zun
    0.08
     פחות
    0.08
     alors
    0.08
     homeland
    0.08
     marin
    0.08
     cláss
    0.08
    Adapters
    0.08
    119
    0.08
     roman
    0.08
     identité
    0.08
    Act Density 0.003%

    No Known Activations