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

    Neuronpedia

    INDEX
    Explanations

    bell

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ventional
    -0.07
    四方
    -0.07
    溃
    -0.07
    ).</
    -0.07
    -like
    -0.07
    arg
    -0.06
    喋
    -0.06
    transport
    -0.06
    rieved
    -0.06
    額
    -0.06
    POSITIVE LOGITS
    $"
    0.08
     справ
    0.08
     dúvida
    0.07
    .previous
    0.07
     INPUT
    0.07
    江门
    0.07
    >';
    0.07
     stance
    0.07
     litigation
    0.07
    -this
    0.07
    Act Density 0.000%

    No Known Activations