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

    Neuronpedia

    INDEX
    Explanations

    references to theorems in mathematical texts

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

    theorem references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Inside
    -0.48
     Cassidy
    -0.47
     Caddy
    -0.47
    INSIDE
    -0.47
    PAI
    -0.45
    Whilst
    -0.45
    |}{}
    -0.45
     Cassie
    -0.44
    stick
    -0.44
    Separated
    -0.43
    POSITIVE LOGITS
     theorem
    2.16
     Theorem
    2.00
    Theorem
    1.89
    theorem
    1.78
     theorems
    1.73
     THEOREM
    1.59
     Theorems
    1.57
    THEOREM
    1.32
     teore
    0.90
    thm
    0.72
    Act Density 0.027%

    No Known Activations