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

    Neuronpedia

    INDEX
    Explanations

    contexts emphasizing the concept of importance

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

    importance of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     StringField
    -0.51
     Cæsar
    -0.50
    testens
    -0.48
    lyser
    -0.48
    shirt
    -0.47
    Cached
    -0.47
    Diplom
    -0.47
    setColumns
    -0.46
     diplomatic
    -0.46
    Installed
    -0.46
    POSITIVE LOGITS
     importance
    1.94
     Importance
    1.80
    Importance
    1.73
    importance
    1.71
     importancia
    1.39
    importanza
    1.30
     importância
    1.29
     significance
    1.23
     importanza
    1.22
     Bedeutung
    1.21
    Act Density 0.011%

    No Known Activations