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

    Neuronpedia

    INDEX
    Explanations

    sections or components of documents discussing various parts or elements

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

    segment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wśród
    -0.41
     cittadino
    -0.39
     plegable
    -0.39
     dezelve
    -0.38
     zoude
    -0.37
     vů
    -0.36
    IActionResult
    -0.36
    śród
    -0.36
     vaste
    -0.36
     parmi
    -0.35
    POSITIVE LOGITS
     thingy
    0.71
     PART
    0.66
    Part
    0.63
     stuff
    0.63
     part
    0.62
     Part
    0.62
     PARTS
    0.60
     Bagian
    0.59
     Parts
    0.59
     STUFF
    0.58
    Act Density 0.037%

    No Known Activations