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

    Neuronpedia

    INDEX
    Explanations

    live

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     proudly
    -0.07
    ミュ
    -0.07
     audience
    -0.06
     surfing
    -0.06
     SizedBox
    -0.06
    826
    -0.06
    CLUD
    -0.06
    SAVE
    -0.06
     cartridge
    -0.06
     BindingFlags
    -0.06
    POSITIVE LOGITS
    рок
    0.06
     正
    0.06
    .ones
    0.06
     физ
    0.06
    倉
    0.06
    mal
    0.06
    赫
    0.06
    شة
    0.06
    تك
    0.06
    .Option
    0.06
    Act Density 0.014%

    No Known Activations