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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ::=
    0.68
     powin
    0.66
     your
    0.64
    夠
    0.63
    ควร
    0.61
     ενη
    0.61
     Slob
    0.59
     соотно
    0.59
    Divide
    0.58
     harus
    0.58
    POSITIVE LOGITS
    వ
    0.77
     그는
    0.75
     उन्‍होंने
    0.74
    ülés
    0.72
    рија
    0.71
    ydı
    0.70
    யின்
    0.68
    但他
    0.68
    性的
    0.68
    他也
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.