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

    Neuronpedia

    INDEX
    Explanations

    letter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    的事情
    -0.07
    --------------↵
    -0.06
     mieux
    -0.06
    _Click
    -0.06
    ูรณ
    -0.06
     buena
    -0.06
     ölç
    -0.06
    -learning
    -0.06
    ysl
    -0.06
    生
    -0.06
    POSITIVE LOGITS
    纳
    0.07
    věl
    0.07
    ederal
    0.06
     나오
    0.06
    ーダ
    0.06
     vnode
    0.06
     spawning
    0.06
    κα
    0.06
     announcements
    0.06
    Dod
    0.06
    Act Density 0.022%

    No Known Activations