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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Seventeen
    1.02
    <unused2204>
    0.96
     seamen
    0.94
    removeAttr
    0.94
    旕
    0.92
     seizures
    0.91
    国防
    0.91
    淥
    0.90
    㞖
    0.90
     எ
    0.90
    POSITIVE LOGITS
    din
    0.78
    are
    0.71
    berge
    0.71
    sinh
    0.71
    dll
    0.69
     Mere
    0.67
    ulie
    0.66
    enzi
    0.66
    rà
    0.66
    ിക
    0.65
    Act Density 0.000%

    No Known Activations