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

    Neuronpedia

    INDEX
    Explanations

    school

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     outer
    -0.29
     still
    -0.28
    伤
    -0.25
     supers
    -0.25
    ãģ¿ãģªãģķãĤĵ
    -0.24
     proven
    -0.24
     evidence
    -0.24
    incip
    -0.24
     Http
    -0.23
    ä¸Ńåįİ
    -0.23
    POSITIVE LOGITS
    extracomment
    0.27
    erable
    0.27
     ReturnType
    0.26
    \Bridge
    0.26
     Representatives
    0.25
    ndx
    0.25
     Seeds
    0.25
    Cards
    0.25
     Cards
    0.25
    ĵåIJį
    0.25
    Act Density 0.002%

    No Known Activations