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

    Neuronpedia

    INDEX
    Explanations

    functions and parameters related to programming and data management concepts

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

    add, duplicate, find, copy, reuse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vagues
    -0.26
     Cliquez
    -0.26
    こち
    -0.23
     Szw
    -0.23
     salles
    -0.23
    Record
    -0.22
    I
    -0.21
     King
    -0.21
     obie
    -0.21
    NE
    -0.21
    POSITIVE LOGITS
    [@BOS@]
    0.85
    <unused68>
    0.85
    <unused41>
    0.85
    <unused14>
    0.85
    <unused74>
    0.85
    <unused1>
    0.85
    <unused17>
    0.85
    <unused23>
    0.85
    <unused52>
    0.85
    <unused3>
    0.84
    Act Density 0.076%

    No Known Activations