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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    äische
    0.86
    ény
    0.81
    сё
    0.80
    щение
    0.79
    ierna
    0.79
    ərd
    0.79
    녈
    0.79
    freien
    0.78
    nSamples
    0.78
    kách
    0.76
    POSITIVE LOGITS
    C
    0.82
    Warrior
    0.78
    B
    0.75
    Au
    0.73
    S
    0.72
    Tang
    0.71
    D
    0.71
    Quem
    0.70
    Game
    0.69
    I
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.