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

    Neuronpedia

    INDEX
    Explanations

    best options, Arndt, max_val

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     laptops
    0.79
     siti
    0.77
     time
    0.77
     sít
    0.76
     honeymoon
    0.74
    owness
    0.73
    ServiceGroupID
    0.73
     interess
    0.71
    StartTime
    0.70
    fruits
    0.70
    POSITIVE LOGITS
     வகையில்
    0.80
     아무
    0.76
     利用
    0.75
    వా
    0.75
     ஓர்
    0.74
                     
    0.73
     品
    0.73
    าร์
    0.72
        
    0.72
    只
    0.71
    Act Density 0.000%

    No Known Activations