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

    Neuronpedia

    INDEX
    Explanations

    phrases related to high performance or quality in technology

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

    Followed by properties or definitions

    np_acts-logits-general · gemini-2.0-flash

    high quality descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     canina
    -0.53
     Dede
    -0.52
    ByVersion
    -0.51
     zape
    -0.49
    tagHelperRunner
    -0.49
     nhàng
    -0.49
    RuleContext
    -0.49
    edly
    -0.48
     otak
    -0.47
     Lordships
    -0.47
    POSITIVE LOGITS
    WriteBarrier
    0.64
    SerializedSize
    0.64
    Vidite
    0.60
    queryInterface
    0.59
     purity
    0.58
     strength
    0.56
     [{
    0.53
     efficiency
    0.50
    pellier
    0.49
     definition
    0.49
    Act Density 0.161%

    No Known Activations