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

    Neuronpedia

    INDEX
    Explanations

    mandatory conditions and requirements in programming or algorithms

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

    options, arguments, and validation rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.87
     surla
    -0.81
     estekak
    -0.81
     propOrder
    -0.79
    expandindo
    -0.77
     للاسماء
    -0.75
    fromnode
    -0.73
    IndentedString
    -0.72
    Autoritní
    -0.71
    MessageTagHelper
    -0.69
    POSITIVE LOGITS
     real
    0.33
     upper
    0.32
     afges
    0.31
    合う
    0.30
     suitable
    0.30
     BUTLER
    0.29
     bilo
    0.29
     either
    0.28
     type
    0.28
     туда
    0.28
    Act Density 0.007%

    No Known Activations