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

    Neuronpedia

    INDEX
    Explanations

    game-related instructions and actions within a gaming context

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

    Imperative verbs and punctuation

    np_acts-logits-general · gemini-2.0-flash

    commands to achieve objectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TypedDataSet
    -0.64
    +#+#
    -0.53
     Vikipedi
    -0.51
    EndContext
    -0.51
    HideFlags
    -0.50
     StatefulWidget
    -0.50
     GeoNames
    -0.49
    momix
    -0.48
    ocino
    -0.48
    ウンサー
    -0.47
    POSITIVE LOGITS
     defeating
    1.09
     defeat
    0.94
     Defeat
    0.92
     collecting
    0.91
     collect
    0.89
     unlocking
    0.88
     beating
    0.87
     completing
    0.86
     players
    0.85
     derrot
    0.84
    Act Density 0.184%

    No Known Activations