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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    漫
    -0.07
     ένας
    -0.07
    인증
    -0.06
    ivors
    -0.06
     dosud
    -0.06
     vx
    -0.06
     NAN
    -0.06
     یعنی
    -0.06
    flater
    -0.06
    }catch
    -0.06
    POSITIVE LOGITS
    `)↵
    0.07
     โปร
    0.07
    PI
    0.06
     Log
    0.06
    ギ
    0.06
     Greek
    0.06
    _DECL
    0.06
    (s
    0.06
    ,Integer
    0.06
    (*
    0.06
    Act Density 0.001%

    No Known Activations