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

    Neuronpedia

    INDEX
    Explanations

    table comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }\|\
    0.41
     افزایش
    0.41
     आदित्यनाथ
    0.40
     повышения
    0.40
     incremento
    0.39
     bearer
    0.39
    醯
    0.38
    öglichkeiten
    0.38
    ↵↵↵↵↵↵↵↵↵↵
    0.38
    ührung
    0.37
    POSITIVE LOGITS
    PRNewswire
    0.39
    PR
    0.38
     (
    0.38
     PR
    0.36
     Pre
    0.36
    $/
    0.36
     /
    0.36
    Pre
    0.36
     Brun
    0.35
    E
    0.35
    Act Density 0.001%

    No Known Activations