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

    Neuronpedia

    INDEX
    Explanations

    drawing graphics code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Double
    -0.07
    仙境
    -0.07
    ➾
    -0.06
    Thinking
    -0.06
    隶
    -0.06
     hoc
    -0.06
    副主任
    -0.06
     Horny
    -0.06
    海拔
    -0.06
    .routes
    -0.06
    POSITIVE LOGITS
     costs
    0.08
    (fp
    0.07
    きれい
    0.07
    loss
    0.07
    平常
    0.07
    竞赛
    0.07
     steep
    0.06
     تص
    0.06
    stores
    0.06
     still
    0.06
    Act Density 0.004%

    No Known Activations