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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _MARGIN
    -0.06
    'M
    -0.06
     slun
    -0.06
    _dual
    -0.06
    paralle
    -0.06
     ماشین
    -0.06
    备注
    -0.06
     موضوع
    -0.06
    ائلة
    -0.06
     cosm
    -0.06
    POSITIVE LOGITS
    .ones
    0.08
    �始化
    0.07
    uso
    0.07
    /il
    0.07
     wealth
    0.07
     Legends
    0.06
    lights
    0.06
     finanzi
    0.06
    quete
    0.06
    ddb
    0.06
    Act Density 0.000%

    No Known Activations