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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     into
    0.61
    islation
    0.60
     extremely
    0.60
     segregation
    0.59
     setter
    0.57
    macher
    0.56
    极
    0.55
     actually
    0.53
    stone
    0.53
    wonder
    0.53
    POSITIVE LOGITS
     programma
    0.96
    命令行
    0.95
     programa
    0.93
     comandos
    0.93
     programas
    0.91
     programmi
    0.89
    プログラム
    0.86
    程序的
    0.84
     программы
    0.84
    コマンド
    0.84
    Act Density 1.238%

    No Known Activations