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

    Neuronpedia

    INDEX
    Explanations

    then

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ор
    -0.07
    _WATCH
    -0.07
    decltype
    -0.07
     byt
    -0.07
    Nil
    -0.07
     dirent
    -0.06
    مع
    -0.06
    _vector
    -0.06
    @store
    -0.06
    .ylabel
    -0.06
    POSITIVE LOGITS
    .Ab
    0.08
     pared
    0.06
     lớp
    0.06
     QU
    0.06
    _ACTION
    0.06
    ):-
    0.06
     góc
    0.06
    oningen
    0.06
    rats
    0.06
     cidade
    0.06
    Act Density 0.053%

    No Known Activations