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

    Neuronpedia

    INDEX
    Explanations

    m

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _visitor
    -0.06
     Pavel
    -0.06
     proceed
    -0.06
     xa
    -0.06
    );
↵
↵
↵
    -0.06
    ;
↵
↵
↵
    -0.06
    NO
    -0.06
     Excellence
    -0.06
    no
    -0.06
    .Uri
    -0.06
    POSITIVE LOGITS
    _DRIVE
    0.07
     cev
    0.06
     skeletons
    0.06
    主義
    0.06
    enerative
    0.06
     (()
    0.06
    ')]↵
    0.06
     atrib
    0.06
     ==>
    0.06
    qui
    0.06
    Act Density 0.006%

    No Known Activations