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

    Neuronpedia

    INDEX
    Explanations

    robes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     roommate
    -0.08
     welcome
    -0.08
     monday
    -0.08
    _password
    -0.08
     september
    -0.07
    知乎
    -0.07
     roommates
    -0.07
     sidewalk
    -0.07
     fingerprint
    -0.07
     rak
    -0.07
    POSITIVE LOGITS
     impec
    0.09
     Starg
    0.08
     magnifiques
    0.08
     swirling
    0.08
    जे
    0.08
    Muito
    0.08
    Variant
    0.07
    केत
    0.07
     Dí
    0.07
     magnific
    0.07
    Act Density 0.014%

    No Known Activations