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

    Neuronpedia

    INDEX
    Explanations

    numerical identifiers and specific product references

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

    Mac App Store links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused68>
    -0.73
    <unused42>
    -0.73
    <unused23>
    -0.73
    <unused41>
    -0.73
    [@BOS@]
    -0.73
    <pad>
    -0.73
    <unused8>
    -0.73
    <unused14>
    -0.73
    <unused74>
    -0.73
    <unused3>
    -0.73
    POSITIVE LOGITS
    WebServlet
    0.43
    Amazon
    0.35
     AssemblyVersion
    0.32
     Amazon
    0.31
    sidemargin
    0.31
     createSlice
    0.27
     TextInputType
    0.26
    1
    0.26
    let
    0.26
    Pure
    0.26
    Act Density 0.003%

    No Known Activations