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

    Neuronpedia

    INDEX
    Explanations

    used prior to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Không
    0.39
    Không
    0.36
    0
    0.32
     گ
    0.31
    मु
    0.31
     ઓ
    0.31
     знамени
    0.30
     소프트
    0.30
    G
    0.30
    мо
    0.30
    POSITIVE LOGITS
     altres
    0.34
    veratrol
    0.33
     abreast
    0.33
     striées
    0.33
     kiles
    0.31
    बीयत
    0.31
     etcétera
    0.31
     retorted
    0.31
    ఆర్‌
    0.30
     गिरफ्त
    0.30
    Act Density 0.370%

    No Known Activations