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

    Neuronpedia

    INDEX
    Explanations

    grad

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     psychology
    -0.07
     Psychology
    -0.06
    ynamodb
    -0.06
    ober
    -0.06
    ेह
    -0.06
    apyrus
    -0.06
    Room
    -0.06
     ря
    -0.06
     paired
    -0.06
     unwitting
    -0.06
    POSITIVE LOGITS
    nave
    0.07
     Fred
    0.07
    .gradle
    0.07
     برنامه
    0.07
     FAA
    0.06
    (Grid
    0.06
     Gad
    0.06
    .StackTrace
    0.06
     هنر
    0.06
    grade
    0.06
    Act Density 0.003%

    No Known Activations