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

    Neuronpedia

    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Antique
    -0.08
     |/
    -0.07
     Tools
    -0.07
     Compare
    -0.07
    azole
    -0.07
    婚纱
    -0.07
    تب
    -0.07
    ieber
    -0.07
    ascus
    -0.06
    促成
    -0.06
    POSITIVE LOGITS
     gost
    0.08
    强国
    0.07
     programmers
    0.07
    告诉我
    0.07
    ⇛
    0.07
    .Inst
    0.07
    减值
    0.06
    .Region
    0.06
     />
↵
    0.06
    Fort
    0.06
    Act Density 0.084%

    No Known Activations