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

    Neuronpedia

    INDEX
    Explanations

    terms related to teams and organizations

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

    organization, location, or structure names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.55
     nonUne
    -0.42
    Referanser
    -0.41
    KommentareTeilen
    -0.40
    awtextra
    -0.38
     {?}
    -0.36
    Portály
    -0.36
     stanie
    -0.35
     térmica
    -0.35
    Portail
    -0.35
    POSITIVE LOGITS
    SceneManagement
    0.46
     Nere
    0.43
    estacks
    0.43
    URLEncoder
    0.43
    ⌉
    0.43
     Calam
    0.42
    ceeds
    0.42
     barrel
    0.41
     Offizielle
    0.41
    preventDefault
    0.40
    Act Density 0.458%

    No Known Activations