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

    Neuronpedia

    INDEX
    Explanations

    challenges, starts, strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Third
    0.52
     Suicide
    0.47
     Graduate
    0.47
     Resources
    0.46
    માં
    0.46
     Eye
    0.46
     Apps
    0.46
     Swarovski
    0.46
     Structural
    0.45
     Tread
    0.45
    POSITIVE LOGITS
    рей
    0.51
    ઢી
    0.50
     rarement
    0.48
     punishable
    0.48
    щён
    0.47
     selten
    0.47
    (")
    0.47
     \%)$.
    0.46
    тивной
    0.46
    ("
    0.46
    Act Density 0.001%

    No Known Activations