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

    Neuronpedia

    INDEX
    Explanations

    references to programming libraries and functions, particularly related to system calls and their handling

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

    python module usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.51
    -
    -0.36
    ;
    -0.36
    ­
    -0.35
    <eos>
    -0.34
    /
    -0.34
    s
    -0.32
    .
    -0.30
    )
    -0.30
    –
    -0.29
    POSITIVE LOGITS
    <unused74>
    1.31
    <unused41>
    1.31
    <unused8>
    1.31
    [@BOS@]
    1.30
    <unused51>
    1.30
    <unused23>
    1.30
    <unused42>
    1.30
    <unused28>
    1.30
    <unused14>
    1.30
    <unused16>
    1.30
    Act Density 0.024%

    No Known Activations