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

    Neuronpedia

    INDEX
    Explanations

    technical terms and phrases related to programming errors and debugging

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

    Numbers within code or identifiers

    np_acts-logits-general · gemini-2.0-flash

    edits to, else express

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ImageContext
    -0.87
    MLLoader
    -0.80
    endphp
    -0.70
    SBATCH
    -0.62
    Smarty
    -0.61
    StructEnd
    -0.61
     ErrIntOverflow
    -0.59
    tolsó
    -0.58
    RRect
    -0.55
     <",
    -0.55
    POSITIVE LOGITS
     id
    0.56
     withRouter
    0.53
    7
    0.52
    ItemId
    0.51
    id
    0.49
    8
    0.49
    3
    0.48
     constant
    0.48
    1
    0.48
    9
    0.47
    Act Density 0.663%

    No Known Activations