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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ︶
    -0.07
    .top
    -0.07
    esion
    -0.07
     comple
    -0.07
     anterior
    -0.07
    _break
    -0.07
     apprentices
    -0.07
    脔
    -0.07
     reuse
    -0.07
    مشاهدة
    -0.07
    POSITIVE LOGITS
    意识到
    0.07
    我们在
    0.07
    Bat
    0.07
    例子
    0.07
     Ant
    0.06
     Stam
    0.06
     Misc
    0.06
     Ikea
    0.06
     yielding
    0.06
     yt
    0.06
    Act Density 0.012%

    No Known Activations