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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    setPosition
    -0.07
    _MUL
    -0.07
     accelerator
    -0.07
    多样化
    -0.07
    _pid
    -0.07
    wow
    -0.07
    .NumericUpDown
    -0.07
     geld
    -0.07
    Spoiler
    -0.07
    ñana
    -0.07
    POSITIVE LOGITS
     crumbling
    0.07
    cursor
    0.07
    trs
    0.07
    𝅪
    0.07
    (minutes
    0.06
    🏗
    0.06
    쳑
    0.06
    rząd
    0.06
    (Task
    0.06
    matrix
    0.06
    Act Density 0.018%

    No Known Activations