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

    Neuronpedia

    INDEX
    Explanations

    numerical values, particularly in the context of data representation or coding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, paths, or citizen

    np_acts-logits-general · gemini-2.0-flash

    file path, citizen, mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.88
     ſtate
    -0.81
     Anſ
    -0.78
     مشين
    -0.77
     juſ
    -0.76
    存于互联网档案馆
    -0.76
    +#+#
    -0.75
    Rhestr
    -0.75
     deſt
    -0.74
     ſever
    -0.73
    POSITIVE LOGITS
    $__
    0.52
     
    0.51
     $
    0.50
    SaveChangesAsync
    0.46
    RequestMapping
    0.45
     er
    0.45
    nima
    0.44
     i
    0.44
    ↵
    0.43
    ↵↵
    0.43
    Act Density 0.230%

    No Known Activations