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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions, particularly those involving complex notation and functions

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

    LaTeX math mode expressions

    np_acts-logits-general · gemini-2.0-flash

    LaTeX mathematical expressions `${`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AsUp
    -0.78
    bcryptjs
    -0.66
    mazoo
    -0.65
     Pola
    -0.65
     paramInt
    -0.64
    NamedQueries
    -0.62
    </strong>
    -0.61
    didSet
    -0.60
    InteropServices
    -0.59
    manta
    -0.59
    POSITIVE LOGITS
     ${
    1.08
    ${
    0.89
    (${
    0.88
    =${
    0.85
    ="${
    0.84
     متعلقه
    0.81
    -${
    0.79
    :${
    0.79
    ("${
    0.76
     "${
    0.75
    Act Density 0.340%

    No Known Activations