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

    Neuronpedia

    INDEX
    Explanations

    references to influential literary or media figures, specifically within the context of notable works or cultural commentary

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

    Orwell, LLVM, Grace, vm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.46
    ंदीखरीदारी
    -0.39
     Infórmanos
    -0.39
     ворот
    -0.35
     Knife
    -0.35
    maxsize
    -0.33
     vesti
    -0.32
    intendent
    -0.32
    Portale
    -0.32
     rare
    -0.31
    POSITIVE LOGITS
     aDecoder
    0.73
    balleur
    0.72
    ConstraintMaker
    0.70
    tvguidetime
    0.68
     surla
    0.67
    SpringBootTest
    0.67
    Jîn
    0.65
    ніципалі
    0.64
    ########.
    0.63
    bazel
    0.61
    Act Density 0.051%

    No Known Activations