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

    Neuronpedia

    INDEX
    Explanations

    references to copies of software or documents

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

    multiple copies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Behavior
    -0.48
     Behaviors
    -0.46
     behavior
    -0.44
     Yahoo
    -0.43
     behaviors
    -0.42
    Alsace
    -0.42
    Behavior
    -0.42
     Kosovo
    -0.41
    GetField
    -0.41
     comportements
    -0.40
    POSITIVE LOGITS
     copies
    2.08
     Copies
    1.84
    Copies
    1.78
    copies
    1.76
     copy
    1.43
     copias
    1.41
     copie
    1.32
     copia
    1.16
    copy
    1.12
     Copy
    1.12
    Act Density 0.027%

    No Known Activations