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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ease of use and accessibility

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

    easy to use instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zijne
    -0.62
     mijne
    -0.56
     hunne
    -0.55
     zoude
    -0.54
    hésite
    -0.53
     disambiguazione
    -0.53
     nakalista
    -0.50
     ویکی‌پدی
    -0.50
    sproz
    -0.48
    ambién
    -0.48
    POSITIVE LOGITS
    enumi
    0.46
     comprehensive
    0.45
    comprehensive
    0.42
    utiny
    0.42
     accessible
    0.42
     compact
    0.41
     portable
    0.41
    toMap
    0.40
    eddable
    0.40
    Easy
    0.40
    Act Density 0.006%

    No Known Activations