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

    Neuronpedia

    INDEX
    Explanations

    dates

    oai_token-act-pair · gemini-2.0-flash

    locations and dates

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    دانشنامهٔ
    -0.50
    endeu
    -0.47
     number
    -0.47
    ctober
    -0.47
     okay
    -0.46
    Figure
    -0.46
     Lieutenant
    -0.46
    keyColumn
    -0.45
    ...]
    -0.45
    ]",
    -0.45
    POSITIVE LOGITS
     Fig
    1.20
     Gov
    1.14
    Fig
    1.14
     Oct
    1.13
     Sept
    1.05
     Aug
    1.05
     Nov
    1.03
     Feb
    1.03
     Calif
    0.99
     Figs
    0.97
    Act Density 2.168%

    No Known Activations