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

    Neuronpedia

    INDEX
    Explanations

    references to documentation and informational content

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

    at home tours

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     governments
    -0.35
    endix
    -0.34
     Hout
    -0.34
     put
    -0.33
    ця
    -0.33
     cult
    -0.33
    onCancel
    -0.33
     Birth
    -0.32
     Sunshine
    -0.32
     fick
    -0.32
    POSITIVE LOGITS
     &___
    0.75
     utafitiHapana
    0.74
     وتسجيلات
    0.73
     kasarigan
    0.68
    windowFixed
    0.65
     Chwiliwch
    0.63
    ########.
    0.62
    tagHelperRunner
    0.62
    Personendaten
    0.60
     disambiguazione
    0.59
    Act Density 0.000%

    No Known Activations