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

    Neuronpedia

    INDEX
    Explanations

    I am

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     любого
    0.52
    デメリット
    0.47
     ослож
    0.46
    任务
    0.45
     інших
    0.44
     других
    0.43
    尒
    0.42
    鸡
    0.42
     любых
    0.41
    意味着
    0.41
    POSITIVE LOGITS
    daemon
    0.49
     heard
    0.46
     longtime
    0.46
     pobl
    0.44
     cenário
    0.43
     telah
    0.43
     kam
    0.42
     morn
    0.42
     tapas
    0.41
     eighteen
    0.41
    Act Density 0.020%

    No Known Activations