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

    Neuronpedia

    INDEX
    Explanations

    references to languages or terms related to linguistic studies

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

    following "that", "the", "a", "its", or "same"

    np_acts-logits-general · gemini-2.0-flash

    word or proper noun name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    orsese
    -0.54
    OrBuilder
    -0.52
     kaarangay
    -0.43
    }))
    -0.43
    retario
    -0.41
    }));
    -0.40
    FilterChain
    -0.40
    withOpacity
    -0.39
     Arhivirano
    -0.38
    KURZBESCHREIBUNG
    -0.37
    POSITIVE LOGITS
     name
    3.25
     names
    2.82
    name
    2.63
     Name
    2.52
     NAME
    2.48
    Name
    2.33
     Names
    2.28
     Namen
    2.22
    NAME
    2.21
     naam
    2.15
    Act Density 0.871%

    No Known Activations