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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating conditionality and planning

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

    relative specific following tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DeleteBehavior
    -0.47
    CloseOperation
    -0.46
     Normdatei
    -0.43
    principalColumn
    -0.41
     tarko
    -0.38
     puol
    -0.37
    AMILY
    -0.36
    PDOException
    -0.35
    ագրություններ
    -0.35
    complished
    -0.35
    POSITIVE LOGITS
    0.54
    ViewInit
    0.51
     dlatego
    0.46
     utafitiHapana
    0.45
    帖最后由
    0.45
    StoryboardSegue
    0.42
     stiefe
    0.41
     समीक्षक
    0.41
     hại
    0.40
     edit
    0.40
    Act Density 0.101%

    No Known Activations