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

    Neuronpedia

    INDEX
    Explanations

    numeric patterns and specific programming terminology in code snippets

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

    Japanese sentence endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yym
    -0.53
    AnimationsModule
    -0.52
    UnusedPrivate
    -0.51
    afficheront
    -0.48
     estekak
    -0.48
     Photocase
    -0.48
    addCriterion
    -0.48
    ItemBackground
    -0.47
     lenker
    -0.46
    ỡng
    -0.45
    POSITIVE LOGITS
     NSCoder
    0.49
    BeginContext
    0.42
     Chwiliwch
    0.39
     Walkover
    0.37
    oneofs
    0.34
    SequentialGroup
    0.34
     bäst
    0.33
    beforeEach
    0.33
    ställning
    0.32
     défauts
    0.31
    Act Density 0.015%

    No Known Activations