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

    Neuronpedia

    INDEX
    Explanations

    references to phenomena and their characteristics

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

    phenomenon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     définiti
    -0.43
    Stored
    -0.42
    väg
    -0.41
     hjär
    -0.40
    üstung
    -0.40
     becauſe
    -0.40
     Reſ
    -0.40
    dug
    -0.40
     vertrou
    -0.39
     Eſ
    -0.39
    POSITIVE LOGITS
     phenomena
    1.49
     phenomenon
    1.43
     Phenomena
    1.34
     fenomeno
    1.27
    phenomen
    1.16
     Phenomen
    1.16
     fenómeno
    1.16
     phénomènes
    1.13
     fenô
    1.10
     phénomène
    1.09
    Act Density 0.015%

    No Known Activations