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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ARON
    0.91
     detección
    0.89
     говорит
    0.88
    에
    0.83
    Α
    0.82
    Ｂ
    0.79
    embra
    0.78
    Honestly
    0.77
    eroy
    0.77
    𝘽
    0.77
    POSITIVE LOGITS
     monasteries
    0.79
    祺
    0.77
     prosperity
    0.76
    νης
    0.76
     perennials
    0.75
     Scales
    0.73
    堕
    0.73
     animals
    0.73
     Stitch
    0.72
     pesantren
    0.72
    Act Density 0.001%

    No Known Activations