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

    Neuronpedia

    INDEX
    Explanations

    coefficients, guidance, analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     интерфей
    0.39
    ֹ
    0.39
    敵人
    0.38
    Originally
    0.38
    Ideally
    0.38
     opciones
    0.37
     opções
    0.37
     обязанности
    0.37
     oleks
    0.36
    र्क
    0.35
    POSITIVE LOGITS
     wonders
    0.49
     coefficients
    0.47
     wondered
    0.46
     basics
    0.46
     Coefficients
    0.45
     wonder
    0.44
    系数
    0.43
     ged
    0.43
     benefited
    0.42
    coefficient
    0.42
    Act Density 0.000%

    No Known Activations