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

    Neuronpedia

    INDEX
    Explanations

    learning objectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     popping
    0.41
     Freunden
    0.39
     भुवनेश्वर
    0.39
     Lippincott
    0.39
    modulin
    0.39
     这个
    0.39
     Taunton
    0.39
     দেড়
    0.39
    basicConfig
    0.39
     मोदी
    0.38
    POSITIVE LOGITS
     Cust
    0.46
    Atomic
    0.40
     Comp
    0.38
    :",
    0.38
     {,
    0.37
    Cust
    0.37
     مشين
    0.37
    At
    0.36
    อส
    0.36
     atomic
    0.36
    Act Density 0.007%

    No Known Activations