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

    Neuronpedia

    INDEX
    Explanations

    architectural features and details related to church buildings

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

    architectural descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.81
    ſelves
    -0.78
     ſch
    -0.77
     ſche
    -0.77
     utafitiHapana
    -0.74
     purpoſe
    -0.74
     myſelf
    -0.73
     Anſ
    -0.72
     ſind
    -0.71
     Majefty
    -0.70
    POSITIVE LOGITS
     introduced
    0.36
     a
    0.36
     the
    0.35
    introduced
    0.35
     as
    0.34
     introducing
    0.34
    ↵
    0.33
    ,
    0.32
     appearing
    0.32
    ↵↵
    0.32
    Act Density 0.007%

    No Known Activations