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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     cierto
    1.32
    К
    1.14
    𝙜
    1.13
     soothe
    1.12
    𝙮
    1.09
    𝙠
    1.01
     cortic
    1.01
     deceive
    0.99
    Calling
    0.99
     simplify
    0.98
    POSITIVE LOGITS
     частью
    1.13
     cerevisiae
    1.08
     Следу
    1.02
     isothermal
    1.00
    isdigit
    1.00
    ‹
    1.00
    uradaki
    0.99
    it
    0.98
     jerk
    0.98
    maßen
    0.98
    Act Density 0.010%

    No Known Activations