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

    Neuronpedia

    INDEX
    Explanations

    built by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ic
    1.12
    ില്‍
    1.12
    습니다
    1.11
    ının
    1.08
    łej
    1.07
    น้อง
    1.07
    です
    1.06
    ți
    1.05
    ੪
    1.05
    𝒚
    1.04
    POSITIVE LOGITS
    ه
    1.22
    zantine
    1.18
     virtue
    1.13
    y
    1.13
    ARY
    1.09
    ی
    1.09
    衷
    1.09
     EDS
    1.07
    f
    1.07
    a
    1.05
    Act Density 0.171%

    No Known Activations