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

    Neuronpedia

    INDEX
    Explanations

    pioneering sustainable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    เยี่ยม
    0.40
    -
    0.39
    اً
    0.38
     당연
    0.38
     ≤
    0.38
    )
    0.38
    .’
    0.37
    明確
    0.37
    応援
    0.37
    .)
    0.36
    POSITIVE LOGITS
    TakePhoto
    0.45
     ublox
    0.42
    Gioco
    0.41
    Diam
    0.40
     fertilisers
    0.40
    怛
    0.40
    里
    0.40
     creare
    0.40
     QFile
    0.40
     काग
    0.39
    Act Density 0.007%

    No Known Activations