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

    Neuronpedia

    INDEX
    Explanations

    itt

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    quarters
    -0.07
     エ
    -0.06
    plements
    -0.06
     Kur
    -0.06
     aeros
    -0.06
    ida
    -0.06
     Ig
    -0.06
    Non
    -0.06
    λος
    -0.06
    .ip
    -0.06
    POSITIVE LOGITS
    agraph
    0.07
     домашних
    0.07
    \Mail
    0.06
     opět
    0.06
    」的
    0.06
    .testng
    0.06
    '>↵↵
    0.06
     Suppress
    0.06
    าณาจ
    0.06
    -pdf
    0.06
    Act Density 0.015%

    No Known Activations