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
    gallery
    -0.06
    Para
    -0.06
    (pr
    -0.06
    etyl
    -0.06
     Vil
    -0.06
     avez
    -0.06
    yp
    -0.06
     DIR
    -0.06
    <s
    -0.06
    _has
    -0.06
    POSITIVE LOGITS
     sen
    0.07
    _ATTACK
    0.06
     lineman
    0.06
     ipsum
    0.06
     Coconut
    0.06
     Charging
    0.06
     geschichten
    0.06
     funciona
    0.06
    ตรวจ
    0.06
    째
    0.06
    Act Density 0.060%

    No Known Activations