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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    netstandard
    0.82
    cou
    0.80
    其中的
    0.79
     beans
    0.79
     nearest
    0.79
    gende
    0.78
    쇼
    0.77
    其
    0.77
    sketch
    0.77
     su
    0.76
    POSITIVE LOGITS
     уголов
    1.36
    Pregnant
    1.35
     سرمایہ
    1.35
     preclude
    1.28
     преступ
    1.25
     shocked
    1.24
     категори
    1.24
     forbid
    1.22
    eterminate
    1.22
     infine
    1.22
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.