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

    Neuronpedia

    INDEX
    Explanations

    negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Olymp
    -0.08
     Flo
    -0.07
    _received
    -0.07
    獲得
    -0.07
    ازل
    -0.07
     ог
    -0.07
     accompagn
    -0.06
     Cavaliers
    -0.06
    енно
    -0.06
    xcb
    -0.06
    POSITIVE LOGITS
     frameworks
    0.07
     spills
    0.07
     China
    0.06
    rin
    0.06
     textual
    0.06
     framework
    0.06
     padd
    0.06
     planet
    0.06
    reation
    0.06
    егист
    0.06
    Act Density 0.072%

    No Known Activations