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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ఖ్య
    0.63
    酸化
    0.63
    ద్ర
    0.62
    onom
    0.61
     公
    0.60
     anthocyan
    0.57
    名字
    0.56
    ****
    0.56
    API
    0.55
    탭
    0.55
    POSITIVE LOGITS
     loop
    1.35
     Loop
    1.21
    循环
    1.18
    Loop
    1.17
     loops
    1.12
    loop
    1.12
    LOOP
    1.10
     Loops
    1.08
     LOOP
    1.05
     conditionals
    1.04
    Act Density 0.677%

    No Known Activations