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

    Neuronpedia

    INDEX
    Explanations

    Chess notations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     believer
    -0.07
     injust
    -0.06
    bero
    -0.06
    atLng
    -0.06
     bour
    -0.06
    î
    -0.06
     hạt
    -0.06
    enido
    -0.06
    wyn
    -0.06
     bitterness
    -0.06
    POSITIVE LOGITS
    ปก
    0.07
     učitel
    0.07
     کم
    0.07
    .Buffer
    0.06
     aktif
    0.06
    ้องการ
    0.06
     Oc
    0.06
     ig
    0.06
    شود
    0.06
    cj
    0.06
    Act Density 0.001%

    No Known Activations