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

    Neuronpedia

    INDEX
    Explanations

    phrases involving conjunctions and descriptive terms that enhance discussions or reviews

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

    after conjunctions

    np_acts-logits-general · gemini-2.0-flash

    positive descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atz
    -0.57
     même
    -0.53
     egyes
    -0.48
     terkait
    -0.48
     infatti
    -0.47
    either
    -0.47
     mesmo
    -0.47
     anum
    -0.47
    even
    -0.46
    ।
    -0.45
    POSITIVE LOGITS
     pinulongan
    0.97
    Portale
    0.91
    verwijspagina
    0.90
     فريبيس
    0.86
     fun
    0.82
    kheim
    0.82
    μβρίου
    0.82
    ^(@)
    0.81
     tartalomajánló
    0.81
     MainAxisSize
    0.79
    Act Density 0.127%

    No Known Activations