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

    Neuronpedia

    INDEX
    Explanations

    testament to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    etails
    1.21
    ם
    1.15
     decimals
    1.09
    НЫ
    1.09
     nymphs
    1.05
    ין
    1.03
    א
    1.03
    ים
    1.02
     generar
    1.01
    יא
    1.01
    POSITIVE LOGITS
    প
    1.03
    แน่น
    1.01
     reckoned
    0.98
    కి
    0.95
    ნიშვნელ
    0.95
     weren
    0.93
     étaient
    0.91
     ήταν
    0.91
     あなた
    0.89
     ì
    0.88
    Act Density 0.045%

    No Known Activations