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

    Neuronpedia

    INDEX
    Explanations

    terms that indicate causality or determination

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

    what determines outcome or property

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ganzen
    -0.42
     geleden
    -0.41
     Grüsse
    -0.40
     parenchyma
    -0.39
    Specifically
    -0.39
     folha
    -0.39
     Gemeins
    -0.39
    loadAll
    -0.38
    yní
    -0.38
    _{[
    -0.38
    POSITIVE LOGITS
     determines
    0.78
     Determines
    0.68
     dictate
    0.60
    determin
    0.60
     bestimmen
    0.59
     determine
    0.57
     determina
    0.57
     determin
    0.56
     predetermin
    0.56
     dictated
    0.55
    Act Density 0.047%

    No Known Activations