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

    Neuronpedia

    INDEX
    Explanations

    metadata and structural elements in coding or documentation contexts

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

    theorems, corollaries, sections, and pages

    np_acts-logits-general · gemini-2.0-flash

    theorem, corollary, and page references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -0.58
    aneity
    -0.57
    tshell
    -0.52
    tvguidetime
    -0.51
    wack
    -0.45
    pology
    -0.45
    ſchen
    -0.44
     ProtoMessage
    -0.44
    ########.
    -0.44
    cifix
    -0.43
    POSITIVE LOGITS
     Chwiliwch
    0.43
    IContainer
    0.41
    发表于
    0.40
     ब्रेकडाउन
    0.40
    ことになる
    0.39
     prohibido
    0.39
    enschaften
    0.37
     renta
    0.36
    TypedDataSet
    0.35
     yık
    0.35
    Act Density 1.041%

    No Known Activations