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

    Neuronpedia

    INDEX
    Explanations

    Actual versus simulated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _accessible
    -0.07
     zákona
    -0.07
    instruction
    -0.07
    idunt
    -0.06
     وظ
    -0.06
     consisting
    -0.06
     дея
    -0.06
     eing
    -0.06
     وات
    -0.06
    ipv
    -0.06
    POSITIVE LOGITS
     Ky
    0.07
    циональ
    0.07
     cumulative
    0.06
     settling
    0.06
    ért
    0.06
    ers
    0.06
    PT
    0.06
    ")))
    0.06
     Sources
    0.06
     Guide
    0.06
    Act Density 0.001%

    No Known Activations