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

    Neuronpedia

    INDEX
    Explanations

    Comparing to standards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     культуры
    -0.07
    (HttpServletRequest
    -0.06
    "><?=$
    -0.06
     burned
    -0.06
     Rome
    -0.06
    .BorderStyle
    -0.06
     Close
    -0.06
     Dangerous
    -0.06
    	IN
    -0.06
    (strlen
    -0.06
    POSITIVE LOGITS
    =size
    0.07
    duce
    0.07
    --){↵
    0.06
     сок
    0.06
    similar
    0.06
     vývoj
    0.06
    ographed
    0.06
    _xx
    0.06
     또
    0.06
    ائب
    0.06
    Act Density 0.060%

    No Known Activations