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

    Neuronpedia

    INDEX
    Explanations

    play

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yoga
    -0.08
     mese
    -0.08
     DAO
    -0.07
     recovery
    -0.07
    portal
    -0.07
     neoliberal
    -0.07
    ối
    -0.07
     sull
    -0.07
     rebellious
    -0.07
     repayment
    -0.07
    POSITIVE LOGITS
    実況
    0.16
     announ
    0.13
     announcing
    0.13
     announcements
    0.12
     describing
    0.12
     announces
    0.11
    现场直播
    0.11
    announce
    0.11
     announce
    0.11
     commentators
    0.10
    Act Density 0.016%

    No Known Activations