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

    Neuronpedia

    INDEX
    Explanations

    improvement policies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -hover
    -0.06
     verdade
    -0.06
    .df
    -0.06
    :model
    -0.06
     beasts
    -0.06
    Threshold
    -0.06
    CASCADE
    -0.06
    ”
    -0.06
    糖
    -0.06
     کننده
    -0.06
    POSITIVE LOGITS
    郭
    0.08
    .IsNullOr
    0.07
    allery
    0.07
    -system
    0.07
    .UserInfo
    0.06
     -,
    0.06
    alle
    0.06
     příro
    0.06
     Giáo
    0.06
     sequence
    0.06
    Act Density 0.043%

    No Known Activations