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

    Neuronpedia

    INDEX
    Explanations

    code and law

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ันได
    -0.07
    ріп
    -0.07
    cla
    -0.07
     selectors
    -0.07
     Suddenly
    -0.06
    ава
    -0.06
    aly
    -0.06
    人口
    -0.06
    나
    -0.06
    Lista
    -0.06
    POSITIVE LOGITS
    冲
    0.07
     oppose
    0.06
     yandan
    0.06
    +-+-+-+-+-+-+-+-
    0.06
     sensit
    0.06
    (NS
    0.06
    Twenty
    0.06
     cheats
    0.06
     homeland
    0.06
     üye
    0.05
    Act Density 0.000%

    No Known Activations