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

    Neuronpedia

    INDEX
    Explanations

    established characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cuja
    0.38
     peut
    0.37
     peculiarities
    0.37
     Yourself
    0.36
     avec
    0.36
     Annot
    0.36
     Taille
    0.35
     Compatibility
    0.35
     with
    0.35
     numai
    0.34
    POSITIVE LOGITS
     आणि
    0.51
    และการ
    0.47
     మరియు
    0.46
     및
    0.45
     и
    0.44
    และ
    0.44
     மற்றும்
    0.43
     və
    0.42
     và
    0.41
     এবং
    0.40
    Act Density 0.002%

    No Known Activations