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

    Neuronpedia

    INDEX
    Explanations

    references to digital object identifiers (DOIs) in citations

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

    doi.org links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <h3>
    -0.49
    <h4>
    -0.46
    <u>
    -0.46
    <h2>
    -0.45
    7
    -0.45
    <b>
    -0.43
    <h6>
    -0.43
     member
    -0.43
    Member
    -0.40
    FieldBuilder
    -0.40
    POSITIVE LOGITS
    dx
    1.25
     DX
    1.21
    DX
    1.16
     dx
    1.16
     Dx
    1.06
    Dx
    0.95
     getX
    0.86
     maxX
    0.74
    getX
    0.73
     DirectX
    0.68
    Act Density 0.006%

    No Known Activations