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

    Neuronpedia

    INDEX
    Explanations

    code comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     invariant
    -0.08
    ply
    -0.07
    iani
    -0.07
    [(
    -0.07
    icrosoft
    -0.07
    试题
    -0.07
    lst
    -0.07
    -tier
    -0.07
     массив
    -0.07
    _album
    -0.07
    POSITIVE LOGITS
     Needed
    0.08
    .ACCESS
    0.08
    的颜色
    0.07
    にな
    0.07
     eyeb
    0.07
    _cpus
    0.07
    👚
    0.07
     воздейств
    0.06
    headers
    0.06
     다시
    0.06
    Act Density 0.003%

    No Known Activations