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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Hacienda
    0.54
     Eisen
    0.53
    ic
    0.45
     Escape
    0.45
    halt
    0.45
     Nap
    0.44
     ApJ
    0.44
     Pase
    0.44
    ↵
    0.44
    blue
    0.43
    POSITIVE LOGITS
     спор
    0.49
    썼
    0.47
    잦
    0.46
    ूम
    0.45
    槸
    0.44
     поддер
    0.42
     συνέχ
    0.42
    棿
    0.41
    롭
    0.40
    수한
    0.40
    Act Density 0.003%

    No Known Activations