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

    Neuronpedia

    INDEX
    Explanations

    references to specialized terminology and concepts in technical or scientific contexts

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

    Mixtures, Environments, Cells, Systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Paglinawan
    -0.85
     незавершена
    -0.75
     autorytatywna
    -0.74
    новниш
    -0.73
     Wikiseite
    -0.73
     Chwiliwch
    -0.68
     Geſch
    -0.68
     Numerade
    -0.68
    NameInMap
    -0.68
    featureID
    -0.66
    POSITIVE LOGITS
    :
    0.40
     Pant
    0.40
    ↵
    0.39
     Sti
    0.39
     Wer
    0.38
    ↵↵
    0.37
     Bo
    0.36
     Pro
    0.36
     Tra
    0.36
    Intent
    0.36
    Act Density 0.049%

    No Known Activations