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

    Neuronpedia

    INDEX
    Explanations

    academic references or citations in scientific texts

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

    After a colon

    np_acts-logits-general · gemini-2.0-flash

    academic proceedings or research papers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <strong>
    -0.50
    expandindo
    -0.49
    、「
    -0.48
     Mentions
    -0.47
    <h2>
    -0.46
    「
    -0.45
    moji
    -0.45
    尊敬
    -0.45
     Allerdings
    -0.45
    ForValue
    -0.45
    POSITIVE LOGITS
     czyli
    0.80
     how
    0.75
     an
    0.70
     Part
    0.68
    CppCodeGen
    0.68
     what
    0.64
    AsUp
    0.64
     lessons
    0.63
    €“
    0.62
    OGND
    0.62
    Act Density 0.107%

    No Known Activations