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

    Neuronpedia

    INDEX
    Explanations

    grade

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Average
    -0.06
    splash
    -0.06
     закуп
    -0.06
    itian
    -0.06
     sû
    -0.06
     Economic
    -0.06
     town
    -0.06
    quir
    -0.06
     Honor
    -0.06
    stagram
    -0.06
    POSITIVE LOGITS
    -grade
    0.09
     grade
    0.08
     Grade
    0.08
    Grade
    0.07
    iffer
    0.07
    OMUX
    0.07
     conducive
    0.06
     papel
    0.06
    Changes
    0.06
    átor
    0.06
    Act Density 0.007%

    No Known Activations