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

    Neuronpedia

    INDEX
    Explanations

    business, errors, and management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Up
    0.56
     الات
    0.49
     There
    0.49
     Get
    0.48
     Decisions
    0.48
     Use
    0.48
     Even
    0.47
     en
    0.47
     No
    0.47
     Upload
    0.47
    POSITIVE LOGITS
    éli
    0.47
    elian
    0.46
    өк
    0.45
    ต์
    0.42
    ጬ
    0.42
    ژگی
    0.42
    }]}\
    0.42
    EventListener
    0.42
     szá
    0.42
     परिसरात
    0.42
    Act Density 0.000%

    No Known Activations