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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    s
    2.28
    ς
    2.05
    IN
    1.81
    sberg
    1.80
    ON
    1.74
    OUS
    1.72
    U
    1.68
    n
    1.65
    THING
    1.60
    AL
    1.58
    POSITIVE LOGITS
    на
    1.73
    ం
    1.55
     Terbaik
    1.53
     pasando
    1.51
     גדול
    1.46
    opes
    1.44
    *
    1.44
     berkata
    1.43
    ะ
    1.43
     gemakkelijk
    1.42
    Act Density 0.000%

    No Known Activations