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

    Neuronpedia

    INDEX
    Explanations

    references to formal institutions and legal concepts

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

    Followed by "for"

    np_acts-logits-general · gemini-2.0-flash

    two-word phrases and specific contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dollis
    -0.47
     ocasión
    -0.43
     Geschäfte
    -0.43
     manguera
    -0.41
     Darauf
    -0.40
     Anhänger
    -0.40
    codiles
    -0.40
     burbujas
    -0.39
     transférez
    -0.39
     שוליים
    -0.39
    POSITIVE LOGITS
    Portale
    0.57
    setVerticalGroup
    0.49
     betweenstory
    0.48
     Fair
    0.48
     ostavi
    0.47
     IActionResult
    0.47
     IDs
    0.46
     BoxFit
    0.46
     Duk
    0.46
     Supreme
    0.45
    Act Density 0.759%

    No Known Activations