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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itemName
    -0.07
    .conf
    -0.07
    /api
    -0.07
    굵
    -0.07
    年之
    -0.07
    particles
    -0.07
    ធ
    -0.07
    人人都
    -0.07
    充分肯定
    -0.07
    充斥
    -0.07
    POSITIVE LOGITS
     Hav
    0.07
     Nathan
    0.06
     Sa
    0.06
    ("""↵
    0.06
     knocking
    0.06
     convenience
    0.06
    -more
    0.06
    _hr
    0.06
    reeze
    0.06
     Brick
    0.06
    Act Density 0.001%

    No Known Activations