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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and state management elements in code

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

    code properties and parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused79>
    -0.99
     يتيمه
    -0.99
    <unused41>
    -0.98
    <unused52>
    -0.98
    <unused28>
    -0.98
    <unused14>
    -0.98
    <unused8>
    -0.98
    <unused16>
    -0.98
    <unused3>
    -0.98
    [@BOS@]
    -0.98
    POSITIVE LOGITS
     is
    0.30
    ↵↵
    0.27
    <eos>
    0.27
    :
    0.26
     either
    0.25
     should
    0.24
    tonode
    0.24
     type
    0.24
     puertas
    0.24
     względu
    0.24
    Act Density 0.019%

    No Known Activations