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

    Neuronpedia

    INDEX
    Explanations

    code constructs and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ින්
    1.36
    sley
    1.28
    დესაც
    1.25
    ের
    1.20
    luğu
    1.20
     uitz
    1.15
    ség
    1.13
    ovala
    1.13
    lıkla
    1.13
    ことにより
    1.11
    POSITIVE LOGITS
    ie
    1.12
    يء
    1.10
    i
    1.10
    Removed
    1.09
    b
    1.09
    И
    1.05
     Rios
    1.05
     ejec
    1.02
     dosing
    1.02
    ית
    1.02
    Act Density 0.001%

    No Known Activations