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

    Neuronpedia

    INDEX
    Explanations

    defined

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     notebook
    -0.07
    ुभ
    -0.07
     Heck
    -0.06
     Sov
    -0.06
    sprites
    -0.06
     hatten
    -0.06
    _interfaces
    -0.06
     Peaks
    -0.06
     Depths
    -0.06
     Winners
    -0.06
    POSITIVE LOGITS
     سین
    0.06
    ीछ
    0.06
    шая
    0.06
    /bootstrap
    0.06
    -role
    0.06
     Alzheimer
    0.06
    ("""↵
    0.06
     Gather
    0.06
    -placeholder
    0.06
     everywhere
    0.06
    Act Density 0.013%

    No Known Activations