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

    Neuronpedia

    INDEX
    Explanations

    descriptions of historical political and military conflicts

    oai_token-act-pair · gemini-2.0-flash

    intervention

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.77
    InjectAttribute
    -0.71
    ValueStyle
    -0.68
    RegistryLite
    -0.65
    IndentedString
    -0.64
    ]--;
    -0.63
    :✨
    -0.60
    parsedMessage
    -0.58
    ModelSerializer
    -0.57
    spesies
    -0.57
    POSITIVE LOGITS
    astéroïdes
    0.55
    PropertyType
    0.48
     quả
    0.47
     ['./
    0.46
     contact
    0.45
    Rhestr
    0.45
     verw
    0.44
     apparently
    0.44
     bao
    0.44
     Contact
    0.43
    Act Density 1.279%

    No Known Activations