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

    Neuronpedia

    INDEX
    Explanations

    method calls and programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ot
    1.31
    os
    1.23
    on
    1.23
    id
    1.16
    iał
    1.16
    ol
    1.14
    ines
    1.13
    ían
    1.11
    ări
    1.09
    át
    1.09
    POSITIVE LOGITS
    schaft
    1.28
    ่
    1.20
    会
    1.09
     potuto
    1.06
    ية
    1.05
    不做
    1.05
    க்
    1.02
    Renk
    0.98
    ITE
    0.98
    Coupon
    0.98
    Act Density 0.000%

    No Known Activations