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

    Neuronpedia

    INDEX
    Explanations

    scientific references and citations in academic writing

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

    Numbers enclosed in double asterisks

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by journal references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.72
    ruptedException
    -0.59
    ValueStyle
    -0.58
     ROL
    -0.50
    roller
    -0.49
     rolling
    -0.47
     Tole
    -0.46
     Gunt
    -0.46
     getResources
    -0.46
     decompression
    -0.46
    POSITIVE LOGITS
    TypedDataSet
    0.76
    MessageTagHelper
    0.59
    PhysRevLett
    0.58
     فريبيس
    0.58
     autorytatywna
    0.54
    Xna
    0.53
    pédie
    0.53
    hatsu
    0.52
     Hockey
    0.52
    +:+
    0.50
    Act Density 0.394%

    No Known Activations