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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate importance or magnitude regarding concepts

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

    "of [importance/magnitude/sorts/ilk]"

    np_acts-logits-general · gemini-2.0-flash

    importance, significance, or type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Források
    -0.48
     trás
    -0.47
    fromnode
    -0.46
     MessageBoxIcon
    -0.45
    Jegyzetek
    -0.45
    :{
    -0.44
    STIC
    -0.44
    DataAnnotations
    -0.44
    eloma
    -0.43
    MessageTagHelper
    -0.42
    POSITIVE LOGITS
     importance
    0.99
     repute
    0.88
     significance
    0.88
    importance
    0.85
     relevance
    0.82
     ilk
    0.81
     Importance
    0.79
     sorts
    0.78
     magnitude
    0.77
     importancia
    0.77
    Act Density 0.334%

    No Known Activations