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

    Neuronpedia

    INDEX
    Explanations

    expressions of conviction or belief

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

    reaching a conclusion or belief

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Билгалдахарш
    -0.67
     AssemblyTitle
    -0.58
    دانشنامهٔ
    -0.54
     Verſ
    -0.54
     fubject
    -0.54
    MessageTagHelper
    -0.54
    İstin
    -0.54
     houſe
    -0.53
    fromnode
    -0.50
    ❸
    -0.50
    POSITIVE LOGITS
    httphttps
    0.44
     náz
    0.37
     chắn
    0.35
     preferring
    0.35
     prefers
    0.34
     conclusión
    0.33
    setattr
    0.33
    結論
    0.33
     préférence
    0.33
     autorités
    0.32
    Act Density 0.110%

    No Known Activations