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

    Neuronpedia

    INDEX
    Explanations

    references to the significance or importance of various topics and concepts

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

    significance or justification

    np_acts-logits-general · gemini-2.0-flash

    importance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AntiForgeryToken
    -0.54
    GHIJKLM
    -0.53
    酎
    -0.53
    anho
    -0.50
    FieldOffset
    -0.49
    śla
    -0.49
     risol
    -0.49
    odziel
    -0.49
     '{@
    -0.48
    Lösung
    -0.48
    POSITIVE LOGITS
     importance
    1.32
    Importance
    1.28
     Importance
    1.24
    importance
    1.11
     importância
    1.05
     benefits
    0.98
     importancia
    0.96
     Benefits
    0.90
    的重要性
    0.90
    Benefits
    0.86
    Act Density 0.320%

    No Known Activations