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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    麺
    1.33
     Preferably
    1.30
     لوبې
    1.29
     Buenas
    1.24
    cę
    1.23
    getApplication
    1.22
     salespeople
    1.21
     Alors
    1.20
     blanchâtre
    1.19
     velha
    1.19
    POSITIVE LOGITS
     est
    0.95
    xc
    0.92
    SD
    0.91
    Q
    0.89
    ant
    0.88
    ли
    0.88
    ston
    0.87
     cat
    0.86
    бота
    0.85
    est
    0.85
    Act Density 0.000%

    No Known Activations