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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     spécifiques
    0.70
     vielfält
    0.67
     atau
    0.64
     مجموعه
    0.64
     patří
    0.63
    🎶
    0.62
     dilengkapi
    0.62
     sesuai
    0.59
     participé
    0.59
    👌
    0.59
    POSITIVE LOGITS
     unwillingness
    0.76
     miedo
    0.73
    放弃
    0.72
    迅速
    0.70
    เร็ว
    0.70
     pessimism
    0.69
     evitar
    0.67
     असामान्य
    0.67
    ທີ່ຈະ
    0.66
     تغيير
    0.65
    Act Density 0.000%

    No Known Activations