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

    Neuronpedia

    INDEX
    Explanations

    vec, tvec, rvec

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    benzoimidazole
    1.09
     conund
    1.05
     दुरु
    1.03
    他の
    1.02
    螂
    1.01
    yyum
    1.00
    完璧
    1.00
     engulf
    0.99
    ethylsulfanyl
    0.99
    ますが
    0.98
    POSITIVE LOGITS
    ات
    1.71
    s
    1.69
    č
    1.28
    '
    1.24
    ের
    1.18
    ों
    1.13
    ς
    1.13
    க
    1.12
    ਆਂ
    1.08
    f
    1.08
    Act Density 0.056%

    No Known Activations