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

    Neuronpedia

    INDEX
    Explanations

    names followed by descriptors or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.38
    عمل
    0.35
    them
    0.33
    plyr
    0.33
    eduanya
    0.33
    دا
    0.31
    ták
    0.30
    ၻ
    0.30
     उन्ह
    0.30
    bohyd
    0.30
    POSITIVE LOGITS
    :
    0.37
     caliente
    0.35
     ಮ
    0.34
     Mabel
    0.34
     a
    0.33
     zapatos
    0.33
     Roblox
    0.32
     Ryan
    0.32
     Melissa
    0.32
     thriller
    0.31
    Act Density 0.034%

    No Known Activations