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

    Neuronpedia

    INDEX
    Explanations

    Watch movements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     offense
    -0.08
     violência
    -0.08
     nasil
    -0.08
     violate
    -0.08
     separated
    -0.08
    #[
    -0.07
     કો
    -0.07
     Homer
    -0.07
     violation
    -0.07
     estratégico
    -0.07
    POSITIVE LOGITS
     specimens
    0.09
     millis
    0.08
     amateur
    0.08
     mécan
    0.08
     əs
    0.07
     amateurs
    0.07
     regla
    0.07
     Wag
    0.07
     Künd
    0.07
     сот
    0.07
    Act Density 0.008%

    No Known Activations