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

    Neuronpedia

    INDEX
    Explanations

    Jungian, tailor, fats, keys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Judah
    1.37
    ستانی
    1.34
    schnitt
    1.21
    Hemos
    1.18
    oscopic
    1.17
    ിയ
    1.16
    GA
    1.16
    ۣ
    1.15
    ंटिक
    1.14
    \\\\
    1.13
    POSITIVE LOGITS
    ле
    1.75
    '&
    1.37
    ない
    1.35
     hace
    1.32
     demonstra
    1.28
     crash
    1.27
    য়
    1.27
     hé
    1.26
     podrá
    1.26
     funda
    1.26
    Act Density 0.229%

    No Known Activations