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

    Neuronpedia

    INDEX
    Explanations

    oa

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (substr
    -0.28
    å²ŃåįĹ
    -0.28
    讳
    -0.26
    oftware
    -0.26
    stretch
    -0.25
    ỡ
    -0.24
    æĺ¯éĿŀ
    -0.24
     chir
    -0.24
    _runtime
    -0.24
     tune
    -0.24
    POSITIVE LOGITS
    rede
    0.27
    illard
    0.27
    å¹³åĿĩæ°´å¹³
    0.26
    ist
    0.26
    æĹ¢
    0.26
    มà¸Ļ
    0.25
     eben
    0.25
    ocab
    0.25
     ThÆ°
    0.25
    eler
    0.24
    Act Density 1.073%

    No Known Activations