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

    Neuronpedia

    INDEX
    Explanations

    US Court of Appeals documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Saving
    -0.07
    useum
    -0.07
    Jack
    -0.07
    /Login
    -0.07
    уль
    -0.07
    енных
    -0.06
    .Builder
    -0.06
    how
    -0.06
    ộng
    -0.06
    _Show
    -0.06
    POSITIVE LOGITS
     AP
    0.08
     wicked
    0.06
     возраста
    0.06
     AAP
    0.06
    ┴
    0.06
     anon
    0.06
     upheld
    0.06
     rep
    0.06
    <dim
    0.06
    (AP
    0.06
    Act Density 0.004%

    No Known Activations