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

    Neuronpedia

    INDEX
    Explanations

    programming methods related to data retrieval and manipulation

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

    code syntax elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AsUp
    -0.85
    <unused74>
    -0.84
    [@BOS@]
    -0.84
    <unused8>
    -0.84
    <unused42>
    -0.84
    <unused52>
    -0.84
    <unused41>
    -0.84
    <unused23>
    -0.84
    <unused16>
    -0.84
    <unused17>
    -0.84
    POSITIVE LOGITS
    ↵↵↵
    0.40
    -
    0.38
    )
    0.38
    ↵↵
    0.37
    Return
    0.36
     or
    0.36
    <code>
    0.35
    ​
    0.34
    вин
    0.33
    ,
    0.33
    Act Density 0.004%

    No Known Activations