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

    Neuronpedia

    INDEX
    Explanations

    documentation strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     System
    0.65
     중앙
    0.64
     nila
    0.64
     시스템
    0.62
     Personnel
    0.62
     உண்மை
    0.62
    нди
    0.61
     Emer
    0.60
    Emer
    0.60
     PERSONNEL
    0.59
    POSITIVE LOGITS
     bomb
    0.57
     осуществления
    0.57
    แท
    0.53
    μπ
    0.52
     стру
    0.52
    ائج
    0.51
    सिर
    0.50
     செய
    0.49
     palabra
    0.49
    lceil
    0.48
    Act Density 0.223%

    No Known Activations