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

    Neuronpedia

    INDEX
    Explanations

    Questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     horrified
    -0.06
    Union
    -0.06
     Lambda
    -0.06
    保证
    -0.06
     assistants
    -0.06
    確
    -0.06
     rebel
    -0.06
    alardan
    -0.06
    itto
    -0.06
     その他
    -0.06
    POSITIVE LOGITS
    �
    0.07
    (calendar
    0.07
    emporary
    0.07
    \E
    0.07
     pob
    0.06
    -el
    0.06
     rv
    0.06
    onio
    0.06
    λευ
    0.06
    _GPIO
    0.06
    Act Density 0.148%

    No Known Activations