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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    дето
    0.31
    フオク
    0.27
    гну
    0.26
    تين
    0.26
    ціа
    0.26
    гідно
    0.26
    pons
    0.25
    ци
    0.25
    पणे
    0.25
    ърква
    0.25
    POSITIVE LOGITS
     grootste
    0.28
     sacrificio
    0.27
    abhavena
    0.27
     akhir
    0.27
     same
    0.26
     Huge
    0.25
    Same
    0.25
     lainnya
    0.25
    ossal
    0.25
    𝓬
    0.24
    Act Density 6.006%

    No Known Activations