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

    Neuronpedia

    INDEX
    Explanations

    math problems and solutions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ook
    -0.08
     Tule
    -0.08
     Scrum
    -0.08
     makeover
    -0.07
     nk
    -0.07
     انتظام
    -0.07
     Inuit
    -0.07
     kan
    -0.07
     l
    -0.07
     Freel
    -0.07
    POSITIVE LOGITS
    Calculated
    0.10
    少女
    0.09
    Calculate
    0.09
     calculated
    0.09
    Calcul
    0.09
     earnings
    0.09
     суммы
    0.08
     negativity
    0.08
     eigenschappen
    0.08
     стоимости
    0.08
    Act Density 0.139%

    No Known Activations