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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ']))↵↵
    -0.07
    etro
    -0.07
    Thinking
    -0.07
     })↵↵
    -0.07
     del
    -0.07
    𝙥
    -0.07
    જ
    -0.07
    물을
    -0.07
    再
    -0.07
    }")
    -0.07
    POSITIVE LOGITS
     atmos
    0.08
    Playback
    0.08
     martyr
    0.07
     אחרות
    0.07
     רבה
    0.07
    اسم
    0.07
     natives
    0.07
    =tmp
    0.07
    (always
    0.07
     baths
    0.07
    Act Density 0.006%

    No Known Activations