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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .medium
    -0.07
    (Game
    -0.07
    (PC
    -0.07
     interpretations
    -0.07
     rozší
    -0.06
    .setting
    -0.06
     setups
    -0.06
    iosis
    -0.06
     inté
    -0.06
    	Action
    -0.06
    POSITIVE LOGITS
    wdx
    0.07
    마
    0.07
     damn
    0.07
    _of
    0.07
    اسم
    0.06
    ually
    0.06
     tắt
    0.06
    Named
    0.06
    ується
    0.06
    dings
    0.06
    Act Density 0.016%

    No Known Activations