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

    Neuronpedia

    INDEX
    Explanations

    Dialogue and personal stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ax
    -0.07
    ир
    -0.07
     '-';↵
    -0.06
    _item
    -0.06
     Tire
    -0.06
     Trails
    -0.06
     addicts
    -0.06
    .Frame
    -0.06
     GM
    -0.06
    -size
    -0.06
    POSITIVE LOGITS
    estructor
    0.06
    である
    0.06
    шло
    0.06
    检测
    0.06
     meant
    0.06
     منتشر
    0.06
    联合
    0.06
     Soda
    0.06
    dragon
    0.06
    comments
    0.06
    Act Density 0.036%

    No Known Activations