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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Victoria
    -0.07
    -being
    -0.07
     LANGUAGE
    -0.06
    (styles
    -0.06
     BET
    -0.06
     вари
    -0.06
    .Children
    -0.06
    ورا
    -0.06
    BoundingBox
    -0.06
     shoppers
    -0.06
    POSITIVE LOGITS
    mh
    0.07
     красив
    0.07
     spécial
    0.06
     @"↵
    0.06
     consequences
    0.06
     apprec
    0.06
    dep
    0.06
     appropriate
    0.06
     expensive
    0.06
     writ
    0.06
    Act Density 0.025%

    No Known Activations