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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    מוסר
    -0.07
    :\"
    -0.07
    Remote
    -0.07
    𫭼
    -0.06
    难道
    -0.06
    土耳
    -0.06
     Immigration
    -0.06
    ｦ
    -0.06
    ]\
    -0.06
     selectors
    -0.06
    POSITIVE LOGITS
     나오
    0.07
    .flip
    0.07
    	mask
    0.07
     cate
    0.06
    finally
    0.06
     Croat
    0.06
    fh
    0.06
    ➖
    0.06
    inos
    0.06
    circ
    0.06
    Act Density 0.074%

    No Known Activations