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

    Neuronpedia

    INDEX
    Explanations

    receiving awards

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     initComponents
    -0.07
    Ⓝ
    -0.07
     Ramos
    -0.07
    ⨀
    -0.07
    .getOutputStream
    -0.07
    肟
    -0.07
     faux
    -0.07
     Creates
    -0.07
     pequeño
    -0.07
    门店
    -0.07
    POSITIVE LOGITS
     handles
    0.08
    звон
    0.07
    月
    0.07
    调度
    0.06
    איכות
    0.06
    ABLE
    0.06
    부터
    0.06
    iking
    0.06
     Hay
    0.06
    locked
    0.06
    Act Density 0.022%

    No Known Activations