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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Philadelphia
    -0.07
     Chicago
    -0.06
    (';
    -0.06
    andan
    -0.06
    간
    -0.06
     Carey
    -0.06
     locale
    -0.06
    اشت
    -0.06
    .le
    -0.06
    annie
    -0.06
    POSITIVE LOGITS
    (rad
    0.07
    ---↵↵
    0.07
     gathered
    0.06
    _SPEED
    0.06
     uten
    0.06
     dreadful
    0.06
     proti
    0.06
    PRODUCT
    0.06
     kní
    0.06
     prav
    0.06
    Act Density 0.027%

    No Known Activations