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

    Neuronpedia

    INDEX
    Explanations

    C

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     долго
    -0.07
    Salir
    -0.06
     natuur
    -0.06
    .Char
    -0.06
    
    -0.06
    唐
    -0.06
     learns
    -0.06
    AppState
    -0.06
    وح
    -0.06
     invocation
    -0.06
    POSITIVE LOGITS
     examinations
    0.07
     �
    0.07
     examination
    0.07
     موضوع
    0.06
     нашей
    0.06
     additions
    0.06
     assessment
    0.06
     ambition
    0.06
     Examination
    0.06
     relatives
    0.06
    Act Density 0.006%

    No Known Activations