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

    Neuronpedia

    INDEX
    Explanations

    blocks of code related to variable assignments

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

    Code snippets with bracketed expressions

    np_acts-logits-general · gemini-2.0-flash

    code syntax and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.60
    ℤ
    -0.48
     beginnetje
    -0.48
     Reverso
    -0.43
    irs
    -0.43
     Mahl
    -0.42
    /-/
    -0.42
     Wikispecies
    -0.41
    Ellen
    -0.40
    τισ
    -0.40
    POSITIVE LOGITS
    GraphicsUnit
    0.97
    ConstraintMaker
    0.81
    AutoresizingMask
    0.79
     فريبيس
    0.72
     uſed
    0.70
    MessageTagHelper
    0.69
     BoxDecoration
    0.69
     himſelf
    0.68
     vectoriales
    0.67
     themſelves
    0.66
    Act Density 0.036%

    No Known Activations