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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the dollar sign symbol in code snippets

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

    code snippets and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     given
    -0.32
     kait
    -0.31
     cheval
    -0.31
     renon
    -0.31
     in
    -0.31
    期刊论文
    -0.30
    様
    -0.30
    교
    -0.30
    hae
    -0.29
     which
    -0.29
    POSITIVE LOGITS
    elemField
    0.80
    IContainer
    0.69
    GOTREF
    0.69
     estekak
    0.69
    IsMutable
    0.67
     propOrder
    0.67
     zwiſchen
    0.66
     deſſen
    0.66
    <unused16>
    0.65
    <unused17>
    0.65
    Act Density 0.021%

    No Known Activations