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

    Neuronpedia

    INDEX
    Explanations

    languages and verb endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Arts
    0.68
     pool
    0.67
     arts
    0.64
     pec
    0.64
    Arts
    0.63
     fine
    0.62
     key
    0.62
     prim
    0.62
     trust
    0.62
     double
    0.61
    POSITIVE LOGITS
    られる
    1.26
    られた
    1.21
    یدن
    1.21
    거나
    1.18
    نے
    1.15
    られ
    1.15
    نده
    1.14
    ть
    1.13
    ння
    1.07
    нию
    1.06
    Act Density 0.048%

    No Known Activations