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

    Neuronpedia

    INDEX
    Explanations

    mathematical functions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mine
    -0.07
     право
    -0.07
    ultz
    -0.07
    Ted
    -0.06
    -(
    -0.06
     hers
    -0.06
     ”↵
    -0.06
    도로
    -0.06
    LOWER
    -0.06
    _context
    -0.06
    POSITIVE LOGITS
    <IActionResult
    0.07
    .:.:.:.
    0.07
    .Aggressive
    0.07
     jmen
    0.06
    ames
    0.06
    .Per
    0.06
    Bird
    0.06
    (itemId
    0.06
    _was
    0.06
     Gover
    0.06
    Act Density 0.052%

    No Known Activations