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

    Neuronpedia

    INDEX
    Explanations

    data points or numerical values

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

    user input/query

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expliquer
    -0.34
     Carolina
    -0.34
    Carolina
    -0.34
     extranjera
    -0.33
     Einwilligung
    -0.33
     arrep
    -0.32
    carolina
    -0.30
     recevrez
    -0.30
     bakteri
    -0.29
     devriez
    -0.28
    POSITIVE LOGITS
    Personendaten
    0.88
     disambiguazione
    0.79
    OGND
    0.72
    قایناق‌لار
    0.69
    ORAGE
    0.66
    cuador
    0.61
     Scottsdale
    0.60
     
    0.59
     utafitiHapana
    0.59
    Scot
    0.57
    Act Density 0.000%

    No Known Activations