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

    Neuronpedia

    INDEX
    Explanations

    work and material treatments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bangunan
    0.44
    pricing
    0.43
    멩
    0.43
    Argument
    0.42
     পণ্য
    0.42
    金額
    0.41
    Innen
    0.41
    町
    0.41
    negoti
    0.40
    eningkatan
    0.40
    POSITIVE LOGITS
     default
    0.44
     swipe
    0.43
     Swipe
    0.42
     Hills
    0.41
     doré
    0.41
     Wi
    0.39
     hills
    0.39
    classAttribute
    0.39
     microm
    0.38
     Skywalker
    0.38
    Act Density 0.001%

    No Known Activations