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

    Neuronpedia

    INDEX
    Explanations

    Academic citations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pissed
    -0.07
    ched
    -0.07
    criptions
    -0.06
    汨
    -0.06
     crafted
    -0.06
     אישית
    -0.06
    (Api
    -0.06
     throat
    -0.06
    在意
    -0.06
    悠悠
    -0.06
    POSITIVE LOGITS
     ENTER
    0.08
    }));↵
    0.08
    Tesla
    0.07
     superheroes
    0.07
    /releases
    0.07
    )){
    0.07
    ovah
    0.07
     isIn
    0.06
    .sol
    0.06
     Share
    0.06
    Act Density 0.001%

    No Known Activations