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

    Neuronpedia

    INDEX
    Explanations

    cooked

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     POR
    -0.07
     arom
    -0.07
    currency
    -0.07
    alaxy
    -0.06
     SCR
    -0.06
    ραν
    -0.06
     Thatcher
    -0.06
     creation
    -0.06
     byte
    -0.06
     Altın
    -0.06
    POSITIVE LOGITS
     cooked
    0.07
     모르
    0.06
    PBS
    0.06
    !!}↵
    0.06
    may
    0.06
    另外
    0.06
    ({
↵
    0.06
     wont
    0.06
    ]);
↵
↵
    0.06
     Pee
    0.06
    Act Density 0.007%

    No Known Activations