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

    Neuronpedia

    INDEX
    Explanations

    references to package declarations in code

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

    references to software packages or modules

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

    package and import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     carrière
    -0.56
     preocu
    -0.48
    <bos>
    -0.47
     écoute
    -0.47
     oub
    -0.45
    ాన
    -0.45
    うちに
    -0.44
     cordes
    -0.43
    zucker
    -0.43
     сожалению
    -0.43
    POSITIVE LOGITS
    InjectAttribute
    0.72
     ModelExpression
    0.71
     <<<<<<<<<<<<<<
    0.67
     صوتيه
    0.67
    SourceChecksum
    0.63
    msgTypes
    0.62
    期刊论文
    0.62
    verwijspagina
    0.60
     виправивши
    0.59
    arraycopy
    0.59
    Act Density 0.010%

    No Known Activations