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

    Neuronpedia

    INDEX
    Explanations

    Informal, conversational writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itr
    -0.08
    ㅂ
    -0.07
     tee
    -0.07
    .s
    -0.07
     vừa
    -0.07
     shave
    -0.07
     Сов
    -0.06
    갑
    -0.06
     Św
    -0.06
    nya
    -0.06
    POSITIVE LOGITS
    opped
    0.07
    auses
    0.07
    argins
    0.07
    另行
    0.07
    >{!!
    0.07
    和社会
    0.07
     temas
    0.07
    误
    0.07
    bag
    0.07
    orts
    0.07
    Act Density 0.143%

    No Known Activations