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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with 'a' that express some level of importance or utility

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

    "a" followed by beneficial adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Parcelize
    -0.40
    Попис
    -0.35
    adple
    -0.35
     postData
    -0.34
     lẻ
    -0.34
    boucles
    -0.34
    vited
    -0.34
    transQ
    -0.34
    Aktualisiert
    -0.33
    髦
    -0.33
    POSITIVE LOGITS
     basis
    0.58
    Tembelea
    0.54
     XCTest
    0.54
    brunn
    0.53
     provide
    0.51
     framework
    0.50
     groundwork
    0.50
     provides
    0.49
     foundations
    0.49
    ResponseWriter
    0.49
    Act Density 0.032%

    No Known Activations