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

    Neuronpedia

    INDEX
    Explanations

    olympics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     counselors
    -0.08
     roommates
    -0.08
     sticks
    -0.08
     ~/.
    -0.08
    ahin
    -0.07
     voicemail
    -0.07
    rut
    -0.07
    porque
    -0.07
     oled
    -0.07
     ethan
    -0.07
    POSITIVE LOGITS
    赛事
    0.18
     evenement
    0.15
     evenementen
    0.15
     개최
    0.14
     мероприят
    0.14
     мероприятия
    0.13
     Veranstaltungen
    0.13
     행사
    0.13
     acara
    0.13
    開催
    0.13
    Act Density 0.100%

    No Known Activations