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

    Neuronpedia

    INDEX
    Explanations

    debugging and logging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    нулся
    -0.08
     reacting
    -0.08
     reactive
    -0.08
    ಿಶ
    -0.08
     гостини
    -0.08
     вок
    -0.08
     remet
    -0.07
    Passive
    -0.07
     passive
    -0.07
     gastron
    -0.07
    POSITIVE LOGITS
     تفاصيل
    0.09
    详细
    0.09
    .details
    0.09
     dokład
    0.09
    -details
    0.09
     Details
    0.09
     détails
    0.09
     bereits
    0.09
    -detail
    0.09
    詳細
    0.09
    Act Density 0.003%

    No Known Activations