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

    Neuronpedia

    INDEX
    Explanations

    stiffness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (OS
    -0.07
     cpu
    -0.07
     وش
    -0.06
    ۲۱
    -0.06
    X
    -0.06
     ruins
    -0.06
     Onun
    -0.06
    =X
    -0.06
     Ho
    -0.06
    MouseEvent
    -0.06
    POSITIVE LOGITS
     stiffness
    0.08
    .It
    0.07
    brief
    0.07
     disturbing
    0.06
    arro
    0.06
    (signal
    0.06
    appa
    0.06
    fy
    0.06
    هاي
    0.06
    tığ
    0.06
    Act Density 0.001%

    No Known Activations