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

    Neuronpedia

    INDEX
    Explanations

    protrusion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    thinking
    -0.07
    "?
    -0.07
    gger
    -0.07
    INO
    -0.06
     beyond
    -0.06
     자유
    -0.06
    放到
    -0.06
    -details
    -0.06
    _Em
    -0.06
    ?↵
    -0.06
    POSITIVE LOGITS
    $insert
    0.08
     AXIS
    0.07
    .widgets
    0.07
    rollable
    0.07
    \Repository
    0.07
    سعيد
    0.07
     rail
    0.07
    ursal
    0.07
     resh
    0.07
    ithmetic
    0.07
    Act Density 0.013%

    No Known Activations