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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ﮈ
    0.92
     aktu
    0.90
     sekitar
    0.85
     jemand
    0.84
    Stick
    0.82
    Logger
    0.81
    Restrict
    0.81
    Loaded
    0.80
    Adjustment
    0.80
     aeration
    0.80
    POSITIVE LOGITS
    ಿದರೆ
    0.71
     சது
    0.63
    ে
    0.63
    ,
    0.63
    даря
    0.62
     ساق
    0.62
    ಗೆ
    0.61
     lược
    0.61
    arrage
    0.59
    ो
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.