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

    Neuronpedia

    INDEX
    Explanations

    injection sites/administration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Constructor
    -0.07
    whose
    -0.07
     trolling
    -0.06
     nắm
    -0.06
     इन
    -0.06
     Scholar
    -0.06
    \Seeder
    -0.06
    -human
    -0.06
     Bolivia
    -0.06
     guilty
    -0.06
    POSITIVE LOGITS
     пок
    0.07
     müssen
    0.07
     LOGGER
    0.07
     readOnly
    0.07
    Exc
    0.06
    .Enabled
    0.06
    :url
    0.06
     площ
    0.06
     домов
    0.06
    .flatten
    0.06
    Act Density 0.004%

    No Known Activations