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

    Neuronpedia

    INDEX
    Explanations

    especially during

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bitmap
    0.44
    gunakan
    0.42
    fected
    0.42
     ekonomik
    0.42
     aport
    0.41
     Europ
    0.41
     gunakan
    0.41
     touristic
    0.41
    It
    0.40
     (
    0.40
    POSITIVE LOGITS
     Dayton
    0.48
    တွင်
    0.48
     timeliness
    0.44
     Spokane
    0.42
     phthal
    0.42
     খুলনা
    0.41
    raham
    0.41
     garment
    0.40
     Brentwood
    0.40
    apolitan
    0.40
    Act Density 0.003%

    No Known Activations