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

    Neuronpedia

    INDEX
    Explanations

    code identifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     advises
    -0.07
    (Seq
    -0.07
     solve
    -0.07
    授
    -0.06
    'l
    -0.06
    督查
    -0.06
     arrives
    -0.06
     missionaries
    -0.06
     saline
    -0.06
     inspections
    -0.06
    POSITIVE LOGITS
    _flip
    0.07
    最强
    0.07
     Dog
    0.07
    ACKET
    0.07
    castHit
    0.06
     是
    0.06
    imoto
    0.06
    elow
    0.06
    <a
    0.06
    bad
    0.06
    Act Density 0.051%

    No Known Activations