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

    Neuronpedia

    INDEX
    Explanations

    references to technicalities and important details in a detailed description

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

    technical aspects and details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Lähteet
    -0.46
     proudest
    -0.35
    roffen
    -0.35
     rewritten
    -0.33
    分别是
    -0.33
    migrationBuilder
    -0.32
    argout
    -0.32
    GOTREF
    -0.32
     descubierto
    -0.31
    umpulkan
    -0.30
    POSITIVE LOGITS
     details
    1.92
    details
    1.70
     aspects
    1.65
     Details
    1.62
     detail
    1.55
    Details
    1.54
     détails
    1.52
    细节
    1.50
     detalles
    1.49
     detalhes
    1.45
    Act Density 0.205%

    No Known Activations