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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Neat
    0.43
    neat
    0.41
     পরিণত
    0.40
    পট
    0.40
     fugitive
    0.39
    Kang
    0.39
     neat
    0.39
     singleton
    0.38
    यरी
    0.38
    Nuclear
    0.37
    POSITIVE LOGITS
    🈵
    0.41
    を示
    0.38
    われ
    0.38
    PEC
    0.36
    照明
    0.36
    istoire
    0.36
     маник
    0.36
    目光
    0.35
    kec
    0.35
     Trooper
    0.35
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.