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

    Neuronpedia

    INDEX
    Explanations

    affiliate links and advertising

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (conn
    -0.08
     vessel
    -0.08
     deceased
    -0.07
     conducting
    -0.07
     trustee
    -0.07
     Norfolk
    -0.07
    _ru
    -0.07
     reservoir
    -0.07
    DEFINED
    -0.07
     departamento
    -0.07
    POSITIVE LOGITS
     uber
    0.07
    洋
    0.07
     все
    0.07
    获利
    0.07
     Eagle
    0.07
     выбира
    0.07
    .emit
    0.07
    블
    0.07
    淘
    0.06
    天上
    0.06
    Act Density 0.005%

    No Known Activations