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

    Neuronpedia

    INDEX
    Explanations

    closing parenthesis followed by asterisks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    1.73
    ség
    1.73
    schaft
    1.70
    {~
    1.62
     keyst
    1.47
    shower
    1.45
    ಾನೂ
    1.45
    J
    1.41
     showering
    1.41
     adduced
    1.34
    POSITIVE LOGITS
    ه
    3.05
    л
    2.92
    ת
    2.59
    د
    2.52
    𝓲
    2.39
    ی
    2.36
    هي
    2.31
    ி
    2.25
    i
    2.22
    ി
    2.20
    Act Density 0.380%

    No Known Activations