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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to scientific and engineering processes

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

    after uncommon or foreign words

    np_acts-logits-general · gemini-2.0-flash

    actions and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ToProps
    -0.37
    ccional
    -0.36
    ganggu
    -0.35
     Prüfung
    -0.35
    uran
    -0.34
    hely
    -0.34
    zional
    -0.33
    RequestMapping
    -0.33
     karde
    -0.33
     win
    -0.32
    POSITIVE LOGITS
    awtextra
    0.72
    oa̍t
    0.69
    parsedMessage
    0.68
    Personendaten
    0.68
    исленность
    0.67
     pinulongan
    0.66
     kasarigan
    0.60
    featureID
    0.59
    ScopeManager
    0.59
     &___
    0.58
    Act Density 4.871%

    No Known Activations