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

    Neuronpedia

    INDEX
    Explanations

    references to programming tests and related functions

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

    test method calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſeveral
    -0.66
     ſche
    -0.57
     ſmall
    -0.57
     itſelf
    -0.54
     Infór
    -0.53
     ſch
    -0.51
     houſe
    -0.51
     ſtre
    -0.50
     whoſe
    -0.50
     málaga
    -0.50
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.57
    DockStyle
    0.45
    การ
    0.41
     Wille
    0.41
     To
    0.40
     Wil
    0.39
     vực
    0.37
     لات
    0.37
     การ
    0.37
     def
    0.37
    Act Density 0.132%

    No Known Activations