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

    Neuronpedia

    INDEX
    Explanations

    Utilitarianism

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _global
    -0.08
     बेस
    -0.07
     TT
    -0.07
    -global
    -0.07
     밝
    -0.07
     ಮೈ
    -0.07
     globally
    -0.06
    (Global
    -0.06
     Mai
    -0.06
     TY
    -0.06
    POSITIVE LOGITS
    ervolle
    0.09
     vie
    0.09
     cellulite
    0.09
     конкурса
    0.08
     конкур
    0.08
    erea
    0.08
     соревн
    0.08
    ioneer
    0.08
     конкурс
    0.08
     Vuitton
    0.08
    Act Density 0.000%

    No Known Activations