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

    Neuronpedia

    INDEX
    Explanations

    e.g

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    omez
    0.49
     landen
    0.49
     acaso
    0.49
    letal
    0.46
    ppelin
    0.44
    ያንዳ
    0.44
    hauer
    0.43
    amerika
    0.43
    beros
    0.43
    ichtigung
    0.43
    POSITIVE LOGITS
    g
    0.51
     g
    0.47
    n
    0.45
     e
    0.45
    詷
    0.45
    窯
    0.45
    工业
    0.45
    e
    0.44
    गड
    0.44
    r
    0.44
    Act Density 0.071%

    No Known Activations