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

    Neuronpedia

    INDEX
    Explanations

    changes and transfers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Daniels
    -0.07
    Germany
    -0.07
    حدة
    -0.07
    ijing
    -0.07
     Griffin
    -0.06
    Collision
    -0.06
     Volkswagen
    -0.06
    ebilecek
    -0.06
     reporting
    -0.06
    される
    -0.06
    POSITIVE LOGITS
    uale
    0.07
    .PNG
    0.07
     Дж
    0.07
     stew
    0.07
    ,sum
    0.06
    bersome
    0.06
     laten
    0.06
    .Dir
    0.06
     complications
    0.06
     Yelp
    0.06
    Act Density 0.037%

    No Known Activations