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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     loading
    0.49
    loading
    0.46
     bidirectional
    0.45
     author
    0.44
    เสริม
    0.44
    視
    0.44
    $(\
    0.43
     be
    0.43
    boolean
    0.42
     damp
    0.42
    POSITIVE LOGITS
     difficultés
    0.54
     excès
    0.54
     Antennes
    0.51
     extérieures
    0.51
     líneas
    0.50
    وابة
    0.50
    rews
    0.50
    uccio
    0.49
    ciò
    0.49
     vở
    0.49
    Act Density 0.000%

    No Known Activations