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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     grateful
    0.42
    син
    0.42
    bin
    0.41
     carried
    0.40
    getRed
    0.39
    㘿
    0.38
     बड़ी
    0.38
     variation
    0.38
    carried
    0.38
    thanks
    0.37
    POSITIVE LOGITS
    नाला
    0.39
    菇
    0.38
    璃
    0.37
    뿌
    0.35
    aju
    0.35
     ´
    0.35
    BuildActionEntry
    0.35
    azes
    0.34
     Unlock
    0.34
     Einst
    0.34
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.