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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ל
    0.84
    지
    0.81
    GE
    0.81
     frmt
    0.77
    ુ
    0.77
    ре
    0.76
    要
    0.75
    ן
    0.74
    ァ
    0.73
    ри
    0.72
    POSITIVE LOGITS
    cyclopent
    0.78
     joystick
    0.76
    hém
    0.75
     hero
    0.74
     héros
    0.74
     bey
    0.73
     cowboy
    0.73
     지나
    0.73
     druż
    0.72
     homme
    0.71
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.