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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ۓ
    -0.08
     legitim
    -0.07
    templ
    -0.07
    莛
    -0.07
     fascism
    -0.07
    imid
    -0.07
    ὣ
    -0.07
    厖
    -0.07
     dictate
    -0.07
    שמות
    -0.06
    POSITIVE LOGITS
    情节
    0.08
    :hidden
    0.07
                    ↵
    0.07
     adress
    0.07
    炸弹
    0.07
     dividend
    0.07
    져
    0.07
    产权
    0.07
    大楼
    0.07
     System
    0.07
    Act Density 0.000%

    No Known Activations