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

    Neuronpedia

    INDEX
    Explanations

    wishes and greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     அவ்
    0.38
    principles
    0.38
    umont
    0.38
    ungk
    0.38
    த்தகைய
    0.37
    onset
    0.37
    ane
    0.36
    draw
    0.36
     disparities
    0.36
     avances
    0.35
    POSITIVE LOGITS
     עם
    0.44
     무료
    0.42
     Memory
    0.41
     který
    0.39
     కోసం
    0.39
     Magic
    0.39
     มือ
    0.39
     Skype
    0.39
    栤
    0.38
     ద్వారా
    0.38
    Act Density 0.019%

    No Known Activations