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

    Neuronpedia

    INDEX
    Explanations

    words that convey positive descriptions or praises

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

    highly positive descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     régime
    -0.36
     Enterprise
    -0.32
     pouce
    -0.29
     Security
    -0.28
     säker
    -0.27
    UnifiedTopology
    -0.27
    體
    -0.26
     enterprise
    -0.26
     programmet
    -0.26
    Security
    -0.25
    POSITIVE LOGITS
    MessageTagHelper
    0.83
     وتسجيلات
    0.75
    AddTagHelper
    0.73
     esternos
    0.71
     censiti
    0.71
    <unused41>
    0.70
    <unused43>
    0.70
    <unused3>
    0.70
    <unused8>
    0.69
    <unused14>
    0.69
    Act Density 0.026%

    No Known Activations