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

    Neuronpedia

    INDEX
    Explanations

    conditions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Oktober
    -0.08
    igraphy
    -0.07
    ikit
    -0.07
     coronary
    -0.07
    VIEW
    -0.07
    acus
    -0.07
     sách
    -0.07
    锿
    -0.07
    錢
    -0.07
     há
    -0.07
    POSITIVE LOGITS
    .gg
    0.07
    );\
    0.07
    ursions
    0.07
    ']]],↵
    0.06
     העלי
    0.06
     Deferred
    0.06
     dipping
    0.06
    efs
    0.06
    🥃
    0.06
     символ
    0.06
    Act Density 0.001%

    No Known Activations