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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    :
    0.63
    ed
    0.60
    V
    0.55
    es
    0.53
     //
    0.52
    ant
    0.51
    ↵↵
    0.49
    un
    0.49
    //
    0.49
    ;
    0.48
    POSITIVE LOGITS
    тики
    0.55
    titleMargin
    0.51
    ༽
    0.50
     escribir
    0.49
     penumpang
    0.49
     bantuan
    0.48
    跶
    0.48
     músculos
    0.47
    ционной
    0.47
     sasan
    0.47
    Act Density 0.000%

    No Known Activations