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

    Neuronpedia

    INDEX
    Explanations

    terms related to academic or formal documentation and programming contexts

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

    skrivebordet consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.72
     cielos
    -0.50
    Parcelize
    -0.50
     ویکی‌پدی
    -0.49
     CreateTagHelper
    -0.47
     jefes
    -0.47
    Nationalité
    -0.47
    Referanser
    -0.46
    deuse
    -0.46
    原始内容存档于
    -0.45
    POSITIVE LOGITS
     himself
    0.54
     său
    0.50
     Himself
    0.44
    stånd
    0.43
    ėjimas
    0.43
     Pue
    0.42
    galus
    0.42
    Климат
    0.42
     arrangement
    0.42
    arrangement
    0.42
    Act Density 0.397%

    No Known Activations