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

    Neuronpedia

    INDEX
    Explanations

    words followed by or proceeded by hyphens such as 'on-site' and 'in-app'

    oai_token-act-pair · gemini-2.0-flash

    services and location

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.73
     Efq
    -0.66
     purpoſe
    -0.63
     caufe
    -0.60
     ſtate
    -0.59
     évêque
    -0.59
     vecin
    -0.58
     attirer
    -0.57
     fubject
    -0.57
     Peasant
    -0.56
    POSITIVE LOGITS
    |;
    0.62
    zeitige
    0.57
    hysema
    0.55
     Regis
    0.54
    ']]
    0.54
    ("/:
    0.54
    hoon
    0.52
    ammer
    0.52
    {'
    0.52
    {"
    0.52
    Act Density 1.358%

    No Known Activations