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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming code and libraries

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

    technical code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.48
    ,
    -0.37
    -
    -0.36
    ↵↵
    -0.35
    ?
    -0.34
    :
    -0.34
     is
    -0.33
    <eos>
    -0.31
    ↵
    -0.31
    max
    -0.30
    POSITIVE LOGITS
     queſta
    1.18
    <unused74>
    1.12
    <unused79>
    1.12
    <unused8>
    1.12
    <unused28>
    1.12
    <unused16>
    1.11
    <unused23>
    1.11
    <unused14>
    1.11
    [@BOS@]
    1.11
    <unused3>
    1.11
    Act Density 0.022%

    No Known Activations