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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Day
    -0.08
     considerable
    -0.07
    Mailer
    -0.07
     draggable
    -0.07
     nickname
    -0.06
    arest
    -0.06
     TEntity
    -0.06
     robber
    -0.06
    择
    -0.06
    _assert
    -0.06
    POSITIVE LOGITS
    PI
    0.07
    وف
    0.06
    490
    0.06
     Holt
    0.06
     informs
    0.06
    ervatives
    0.06
    ΙΝ
    0.06
    (date
    0.06
    Weapons
    0.05
    forms
    0.05
    Act Density 0.000%

    No Known Activations