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

    Neuronpedia

    INDEX
    Explanations

    Tech Research Solutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    1.85
    o
    1.73
    ai
    1.37
    u
    1.34
    ো
    1.33
    e
    1.30
    is
    1.26
    ia
    1.26
    inak
    1.15
    krank
    1.09
    POSITIVE LOGITS
    لا
    1.30
    מ
    1.23
    ف
    1.17
    )。
    1.15
    లు
    1.13
     powied
    1.11
    이다
    1.10
    ق
    1.10
    ح
    1.06
    ლი
    1.05
    Act Density 0.000%

    No Known Activations