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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     운영
    -0.06
     друж
    -0.06
    xima
    -0.06
     приводит
    -0.06
     جلو
    -0.06
     profit
    -0.06
     fue
    -0.06
    گار
    -0.06
    page
    -0.06
    Kelly
    -0.06
    POSITIVE LOGITS
     Male
    0.08
     Ze
    0.07
    ​↵↵
    0.07
     downloads
    0.07
    elerinde
    0.07
     України
    0.07
     journeys
    0.06
    .OP
    0.06
    /Observable
    0.06
    ael
    0.06
    Act Density 0.063%

    No Known Activations