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

    Neuronpedia

    INDEX
    Explanations

    code snippets related to error handling or diagnostic commands

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

    arrow tokens`>>` `<<`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kild
    -0.57
     NSCoder
    -0.55
     />\
    -0.55
    ynomial
    -0.53
    IsMutable
    -0.52
    mtl
    -0.50
    RotationOrder
    -0.49
     RestTemplate
    -0.49
    BagConstraints
    -0.48
     Bedi
    -0.48
    POSITIVE LOGITS
    >>
    1.91
    >>>
    0.88
    ">>
    0.76
    >>,
    0.75
    )>>
    0.69
    >>>>>
    0.69
    >>>>
    0.66
    <<
    0.65
    >>(
    0.63
    >>;
    0.59
    Act Density 0.010%

    No Known Activations