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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Moses
    0.55
    ING
    0.47
    akura
    0.47
    ($
    0.46
    つの
    0.46
     Jules
    0.46
     T
    0.45
    ppy
    0.44
    Κ
    0.43
    Τ
    0.42
    POSITIVE LOGITS
     volant
    0.54
     ganh
    0.53
     öffentlich
    0.53
     bekannte
    0.52
     solche
    0.52
     činn
    0.51
     veřej
    0.51
     heute
    0.50
     inmun
    0.50
    сред
    0.49
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.