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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     hypersurfaces
    0.93
     Segurança
    0.88
    ดังกล่าว
    0.87
    ופה
    0.86
    ใหญ่
    0.85
    よい
    0.85
    няют
    0.84
    이라고
    0.84
     eleições
    0.82
     เยอะ
    0.82
    POSITIVE LOGITS
    s
    0.80
    ς
    0.70
    ز
    0.69
    Ⅸ
    0.68
    ξι
    0.66
    ત્
    0.64
     stricken
    0.64
     طبی
    0.64
    𝘀
    0.63
    듐
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.