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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ibration
    0.71
    aisesti
    0.70
    olithic
    0.68
    strength
    0.68
    bolic
    0.67
    𓍊
    0.67
    gradient
    0.66
    uple
    0.65
    ool
    0.65
    Alarm
    0.65
    POSITIVE LOGITS
    ក
    0.89
     Lufthansa
    0.83
     businesswoman
    0.81
     ח
    0.80
     duas
    0.80
    じゃない
    0.79
     risco
    0.79
     abiert
    0.78
     informática
    0.78
    ற்புத
    0.76
    Act Density 0.001%

    No Known Activations