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

    Neuronpedia

    INDEX
    Explanations

    references to artificial intelligence and its capabilities

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

    technical terms and archaic spellings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dauern
    -0.47
    Rujuakan
    -0.45
    qrstuvwxyz
    -0.44
     ăn
    -0.39
     Lig
    -0.39
    expandindo
    -0.39
     verzichten
    -0.38
     Oste
    -0.38
    anair
    -0.38
     이
    -0.38
    POSITIVE LOGITS
    SuppressLint
    0.51
    ftance
    0.48
     humanity
    0.48
    migrationBuilder
    0.48
     Majefty
    0.47
     auroit
    0.46
     initComponents
    0.46
     Houſe
    0.44
    haku
    0.43
     CreateTagHelper
    0.42
    Act Density 0.053%

    No Known Activations