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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    不同的
    0.71
    ज़ी
    0.69
     penalties
    0.67
     abuses
    0.66
     innymi
    0.65
    दन
    0.65
    众多
    0.64
     കൂടുതൽ
    0.64
     болезни
    0.64
    哿
    0.64
    POSITIVE LOGITS
     wyb
    0.66
     sofa
    0.65
    meng
    0.63
    anno
    0.61
    aus
    0.61
     haut
    0.60
     Evo
    0.60
     cubo
    0.60
     EVO
    0.60
    mm
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.