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

    Neuronpedia

    INDEX
    Explanations

    data processing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pragma
    -0.07
     gf
    -0.06
     bew
    -0.06
     Dry
    -0.06
    Pop
    -0.06
     OLED
    -0.06
     віднов
    -0.06
    MouseMove
    -0.06
     παν
    -0.06
     blur
    -0.06
    POSITIVE LOGITS
     bởi
    0.07
    0.06
     invis
    0.06
    udiante
    0.06
    ظيف
    0.06
    たし
    0.06
    DOB
    0.06
     UITextView
    0.06
     chết
    0.06
            ↵        ↵
    0.06
    Act Density 0.023%

    No Known Activations