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

    Neuronpedia

    INDEX
    Explanations

    Stories about orphans/single parents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    涔
    -0.08
    wpdb
    -0.08
     Ottawa
    -0.08
    OGRAPH
    -0.07
     России
    -0.07
    杭州市
    -0.07
    -abs
    -0.07
     Git
    -0.07
    -ready
    -0.07
    _MAT
    -0.07
    POSITIVE LOGITS
     teaches
    0.07
    Ж
    0.07
    قول
    0.06
    녀
    0.06
    (QtGui
    0.06
    🛩
    0.06
    (selected
    0.06
    unicorn
    0.06
    ضاف
    0.06
     DataTypes
    0.06
    Act Density 0.051%

    No Known Activations