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

    Neuronpedia

    INDEX
    Explanations

    ;

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Scr
    -0.07
     Guardians
    -0.06
    abd
    -0.06
     foods
    -0.06
    íst
    -0.06
     juni
    -0.06
     food
    -0.06
    gorithms
    -0.06
    ampionship
    -0.06
    =f
    -0.06
    POSITIVE LOGITS
     clarified
    0.07
    이가
    0.06
    ้ำหน
    0.06
    私
    0.06
    지만
    0.06
    ;
    0.06
     headers
    0.06
     perplex
    0.06
    todo
    0.06
     '';↵↵
    0.06
    Act Density 0.023%

    No Known Activations