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

    Neuronpedia

    INDEX
    Explanations

    negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     çev
    -0.07
    	day
    -0.07
    inosaur
    -0.07
     Dept
    -0.06
     gå
    -0.06
    iets
    -0.06
     corps
    -0.06
     Pink
    -0.06
     역사
    -0.06
     walkthrough
    -0.06
    POSITIVE LOGITS
     PHI
    0.07
    .AddScoped
    0.07
     힘
    0.07
    _updated
    0.06
     encouraged
    0.06
    '/>↵
    0.06
    lf
    0.06
    _FOR
    0.06
    cido
    0.06
     따른
    0.06
    Act Density 0.203%

    No Known Activations