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

    Neuronpedia

    INDEX
    Explanations

    respectively

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /key
    -0.07
     tul
    -0.06
    .read
    -0.06
    -large
    -0.06
     krat
    -0.06
     tamamen
    -0.06
     sled
    -0.06
    /arch
    -0.06
     KE
    -0.06
     Regional
    -0.06
    POSITIVE LOGITS
    ْم
    0.08
    转
    0.08
    "]]
    0.07
    oppers
    0.07
     fret
    0.06
     числа
    0.06
    ίνει
    0.06
     <=>
    0.06
     contributor
    0.06
     बढ़
    0.06
    Act Density 0.005%

    No Known Activations