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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and their associated attributes or titles

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

    names of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     iprot
    -0.49
    enderror
    -0.48
    PreExecute
    -0.43
    PRNewswire
    -0.41
     spett
    -0.39
    DoubleQuotes
    -0.39
    queles
    -0.39
    antMatchers
    -0.39
    ideae
    -0.38
     jangka
    -0.38
    POSITIVE LOGITS
     Godwin
    0.55
     Mercy
    0.54
    Mercy
    0.52
    OGND
    0.49
    Samson
    0.47
     Samson
    0.47
     Blessing
    0.46
     Moses
    0.46
     Benson
    0.45
     Kingsley
    0.44
    Act Density 0.017%

    No Known Activations