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

    Neuronpedia

    INDEX
    Explanations

    consistently below, why, reason

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bing
    1.39
    र्भ
    1.27
    или
    1.27
    ming
    1.19
     eens
    1.18
    fø
    1.15
    ro
    1.15
    ер
    1.12
    albeit
    1.11
     обе
    1.11
    POSITIVE LOGITS
     Không
    1.23
     welchem
    1.19
     tranquille
    1.16
     subtitles
    1.15
     skoro
    1.15
     flair
    1.10
    कांग्रेस
    1.10
    लोकन
    1.08
     jeśli
    1.08
     Mahama
    1.06
    Act Density 0.000%

    No Known Activations