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

    Neuronpedia

    INDEX
    Explanations

    lifeline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    xcodep
    0.43
    Composite
    0.39
    uern
    0.38
     ڈال
    0.37
    abilität
    0.36
     करनी
    0.36
    aop
    0.36
    ாலும்
    0.36
    trav
    0.36
    尌
    0.36
    POSITIVE LOGITS
     line
    0.44
     un
    0.43
     transformation
    0.42
     previous
    0.41
     former
    0.40
     multiplier
    0.39
     point
    0.37
     old
    0.37
    旧
    0.37
     previously
    0.37
    Act Density 0.005%

    No Known Activations