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

    Neuronpedia

    INDEX
    Explanations

    based on or if provided

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     secretory
    0.44
     Purification
    0.44
     Pelicans
    0.43
     \,\
    0.42
     Natural
    0.42
    atural
    0.42
     coloration
    0.41
     Nitro
    0.41
     Cinema
    0.41
     cellular
    0.41
    POSITIVE LOGITS
    技能
    0.45
    gráf
    0.45
     ошибок
    0.44
     және
    0.42
    字符串
    0.41
    ubuntu
    0.41
     ошиб
    0.41
    чан
    0.40
     definiert
    0.40
    鍗
    0.40
    Act Density 0.002%

    No Known Activations