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

    Neuronpedia

    INDEX
    Explanations

    release of greenhouse gases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    3.78
    ર
    3.11
    lar
    2.80
    u
    2.73
    nya
    2.58
    ع
    2.51
    la
    2.35
    ravel
    2.32
    ال
    2.32
    म
    2.26
    POSITIVE LOGITS
    ियस
    2.20
     Highness
    2.14
     endorph
    2.14
     tla
    2.11
     sheer
    2.06
     ample
    2.04
    ErrorReport
    2.03
     amplitude
    2.02
     intent
    2.00
    鈥
    2.00
    Act Density 0.030%

    No Known Activations