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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     g
    0.74
     gener
    0.72
     Gener
    0.71
     генера
    0.68
    gener
    0.67
    Gener
    0.64
     ge
    0.58
    G
    0.58
     Генера
    0.57
     گ
    0.57
    POSITIVE LOGITS
    basic
    0.84
    Basic
    0.77
     Common
    0.74
     Basic
    0.74
    Common
    0.74
     common
    0.74
    common
    0.72
     basic
    0.71
     कॉमन
    0.70
     BASIC
    0.69
    Act Density 0.000%

    No Known Activations