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

    Neuronpedia

    INDEX
    Explanations

    terms related to naming examples or instances

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

    "...to name a few" or similar phrases

    np_acts-logits-general · gemini-2.0-flash

    just a few

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.95
     gynhyrchwyd
    -0.64
     CreateTagHelper
    -0.60
    endphp
    -0.58
    WebElementEntity
    -0.57
     interesar
    -0.57
     smtplib
    -0.55
    KommentareTeilen
    -0.54
    prüche
    -0.53
     useRouter
    -0.53
    POSITIVE LOGITS
     just
    1.69
    just
    1.48
     Just
    1.29
    Just
    1.28
     among
    1.17
     JUST
    1.12
    JUST
    1.11
    只是
    1.05
    among
    1.03
     merely
    1.01
    Act Density 0.138%

    No Known Activations