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

    Neuronpedia

    INDEX
    Explanations

    protection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    血
    -0.07
     realism
    -0.06
     War
    -0.06
     allies
    -0.06
    kin
    -0.06
     vous
    -0.06
    sy
    -0.06
    _paths
    -0.06
    EST
    -0.06
    Convert
    -0.06
    POSITIVE LOGITS
    ổ
    0.07
     getState
    0.07
     procrast
    0.07
    <lemma
    0.06
    .Cursors
    0.06
    ▋
    0.06
    (example
    0.06
    dür
    0.06
    urança
    0.06
     최고
    0.06
    Act Density 0.006%

    No Known Activations