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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to data handling and querying processes

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

    "example" and a comma

    np_acts-logits-general · gemini-2.0-flash

    introducing examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     niestety
    -0.76
    iestety
    -0.73
    البته
    -0.71
     także
    -0.70
     alfo
    -0.67
     TAMBÉM
    -0.67
    ่านั้น
    -0.66
    espère
    -0.65
     aussi
    -0.65
     myös
    -0.65
    POSITIVE LOGITS
     say
    1.04
    say
    0.95
     Suppose
    0.91
     Say
    0.90
    Say
    0.89
     misalnya
    0.85
    Suppose
    0.82
     bijvoorbeeld
    0.75
     suppose
    0.74
     SAY
    0.72
    Act Density 0.686%

    No Known Activations