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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    awatt
    0.43
     Pyro
    0.40
     Vacation
    0.39
    olong
    0.39
    γγελ
    0.39
    euler
    0.39
    agle
    0.37
    hydro
    0.37
    পেপার
    0.37
     நகா
    0.37
    POSITIVE LOGITS
    擁
    0.42
     elicited
    0.41
     नौ
    0.40
    intl
    0.40
     increments
    0.39
     marketplaces
    0.39
     si
    0.39
    πού
    0.38
    積み
    0.38
     frau
    0.38
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.