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

    Neuronpedia

    INDEX
    Explanations

    open or load

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     patriarch
    -0.07
    ocities
    -0.07
    vanished
    -0.07
     força
    -0.07
    راه
    -0.07
     scorn
    -0.07
    錾
    -0.07
     ensl
    -0.07
    容貌
    -0.07
    арамет
    -0.06
    POSITIVE LOGITS
    BAR
    0.07
    lication
    0.07
    暂停
    0.07
    Building
    0.07
    重庆市
    0.07
     trigger
    0.07
    全文
    0.07
    .spring
    0.07
     Industry
    0.07
    原标题
    0.07
    Act Density 0.004%

    No Known Activations