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

    Neuronpedia

    INDEX
    Explanations

    elements of religious or doctrinal authority

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

    defining action or rule

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AppCompatTheme
    -0.68
     wireType
    -0.66
    ſelben
    -0.64
     Normdatei
    -0.63
     الرياضيه
    -0.63
     ―――――
    -0.63
    OGND
    -0.61
    majánló
    -0.61
    EndInit
    -0.60
    msgTypes
    -0.60
    POSITIVE LOGITS
     what
    0.30
     Hinweis
    0.29
     palavra
    0.28
     Gemeinschaft
    0.28
     What
    0.28
     word
    0.28
     ação
    0.28
     not
    0.27
     that
    0.27
    then
    0.27
    Act Density 0.014%

    No Known Activations