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

    Neuronpedia

    INDEX
    Explanations

    Directness and indirectness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (rp
    -0.07
     Tent
    -0.06
     صورت
    -0.06
    ード
    -0.06
     deep
    -0.06
     Eighth
    -0.06
     worst
    -0.06
    (pi
    -0.06
    —including
    -0.06
    .CompilerServices
    -0.06
    POSITIVE LOGITS
    ////////
    0.07
    ql
    0.06
    aurus
    0.06
    _pages
    0.06
    _KEYBOARD
    0.06
     Kra
    0.06
    backup
    0.06
     Зак
    0.06
     KEY
    0.06
    报
    0.06
    Act Density 0.057%

    No Known Activations