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

    Neuronpedia

    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ريس
    -0.07
    .quest
    -0.06
     Dickens
    -0.06
    我的
    -0.06
    看看
    -0.06
    羽
    -0.06
    -tm
    -0.06
    早
    -0.06
    ुभ
    -0.06
     corners
    -0.06
    POSITIVE LOGITS
     독일
    0.07
    -too
    0.06
    eniable
    0.06
    /sw
    0.06
     œ
    0.06
    symbol
    0.06
    ioms
    0.06
     persone
    0.06
    _UNICODE
    0.06
    abilit
    0.06
    Act Density 0.480%

    No Known Activations