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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     realistic
    -0.08
     பாத
    -0.08
    \Traits
    -0.07
     воздейств
    -0.07
    _ro
    -0.07
     envision
    -0.07
    ='.
    -0.07
    ിയിൽ
    -0.07
     brutal
    -0.07
     glamour
    -0.07
    POSITIVE LOGITS
     conjunction
    0.10
    pron
    0.08
    cca
    0.08
     বাংলা
    0.08
     తెలుగు
    0.08
    ภาษา
    0.08
    atus
    0.08
    語
    0.08
     pronounced
    0.08
     ગુજરાતી
    0.08
    Act Density 0.038%

    No Known Activations