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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    '
    0.64
    ation
    0.48
    L
    0.47
    курс
    0.46
    g
    0.45
    "
    0.44
    +
    0.44
    Zone
    0.43
    S
    0.43
    |
    0.43
    POSITIVE LOGITS
     vyber
    0.52
    ിച്ച്
    0.50
     caballero
    0.49
     വിദ്യാര്‍
    0.49
     romanzo
    0.48
     الوحد
    0.48
     ragazzo
    0.47
     വൈദ്യുതി
    0.47
     pravil
    0.47
     dharma
    0.47
    Act Density 0.000%

    No Known Activations