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

    Neuronpedia

    INDEX
    Explanations

    instances of expressions indicating requests or needs for assistance

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

    technical documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     État
    -0.39
     detalj
    -0.39
     colch
    -0.38
    ABUL
    -0.36
    ),"
    -0.35
    ,"
    -0.34
     odpowied
    -0.34
     suficiente
    -0.33
     Herrn
    -0.33
     goma
    -0.33
    POSITIVE LOGITS
     utafitiHapana
    0.70
     typelib
    0.63
    Viited
    0.63
     autorytatywna
    0.61
     EconPapers
    0.59
    expandindo
    0.58
    Хьажоргаш
    0.56
    تقاوى
    0.56
     wireType
    0.55
    GraphicsUnit
    0.55
    Act Density 0.114%

    No Known Activations