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

    Neuronpedia

    INDEX
    Explanations

    lab procedures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ילה
    -0.07
    Pitch
    -0.07
    (clicked
    -0.07
    (uint
    -0.07
    Widgets
    -0.07
     demo
    -0.07
    Press
    -0.07
     bar
    -0.07
    aidu
    -0.06
     container
    -0.06
    POSITIVE LOGITS
     //'
    0.07
    hunter
    0.07
    웩
    0.07
     oppos
    0.07
    حرك
    0.07
    أد
    0.07
    lopen
    0.07
    ">$
    0.06
    ומנים
    0.06
    ⎯
    0.06
    Act Density 0.071%

    No Known Activations