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

    Neuronpedia

    INDEX
    Explanations

    seemingly random and meaningless characters and formatting

    oai_token-act-pair · gemini-2.0-flash

    Code, math, instructions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     create
    -1.29
     find
    -1.29
     give
    -1.24
     learn
    -1.24
     make
    -1.23
     take
    -1.23
     keep
    -1.22
     apply
    -1.19
     explore
    -1.18
     choose
    -1.17
    POSITIVE LOGITS
     recent
    0.52
     fubject
    0.49
    OutputType
    0.49
    jgl
    0.47
    apimachinery
    0.46
     étoit
    0.46
     mourut
    0.45
     former
    0.45
     sources
    0.42
     background
    0.41
    Act Density 4.644%

    No Known Activations