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

    Neuronpedia

    INDEX
    Explanations

    references to generic programming concepts or types in code

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

    generic example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InitStruct
    -0.41
     fallait
    -0.33
     Flügel
    -0.32
     ferons
    -0.31
     tetap
    -0.30
     exámenes
    -0.30
     hacia
    -0.29
     utanför
    -0.29
     ändå
    -0.28
     prouve
    -0.28
    POSITIVE LOGITS
    Generic
    2.95
     Generic
    2.30
    generic
    2.05
     generic
    2.02
    GENERIC
    1.56
    generics
    1.19
     gener
    1.12
    泛
    0.98
     Gener
    0.96
    Gener
    0.91
    Act Density 0.000%

    No Known Activations