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

    Neuronpedia

    INDEX
    Explanations

    explanations and analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    I
    0.44
     is
    0.44
     an
    0.37
    ،
    0.37
    ni
    0.36
    ny
    0.35
    res
    0.35
    nt
    0.33
    ns
    0.33
    settes
    0.32
    POSITIVE LOGITS
    ב
    0.47
    મ
    0.46
    ك
    0.45
    ר
    0.44
    ور
    0.43
    ب
    0.42
    ம்
    0.42
    w
    0.41
    ו
    0.41
    ת
    0.40
    Act Density 1.480%

    No Known Activations