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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ﺘ
    0.81
    ﺒ
    0.78
     frá
    0.73
    бари
    0.71
    なかった
    0.68
    ັບ
    0.68
     Rew
    0.68
    కోవ
    0.67
     Վ
    0.67
    Ꮄ
    0.67
    POSITIVE LOGITS
    }])
    0.93
     hommes
    0.78
    Servo
    0.77
    0.76
     Интернет
    0.76
    Sierra
    0.75
    Sing
    0.75
    ≐
    0.75
    Internet
    0.74
    0.74
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.