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

    Neuronpedia

    INDEX
    Explanations

    HTML or CSS class attributes

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

    class followed by =

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    -0.44
    ,
    -0.44
    ;
    -0.38
    -,
    -0.35
    -
    -0.32
    、
    -0.32
    .
    -0.31
    –
    -0.31
    ­
    -0.30
    ¬
    -0.30
    POSITIVE LOGITS
    <unused14>
    0.94
    [@BOS@]
    0.94
    <unused42>
    0.94
    <unused80>
    0.94
    <unused51>
    0.94
    <unused43>
    0.94
    <unused52>
    0.94
    <unused41>
    0.94
    <unused8>
    0.94
    <unused16>
    0.94
    Act Density 0.015%

    No Known Activations