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

    Neuronpedia

    INDEX
    Explanations

    HTML head section

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ust
    0.53
    ultur
    0.51
    l
    0.48
    San
    0.47
    rat
    0.46
    Mac
    0.46
    S
    0.45
    lar
    0.44
    St
    0.44
    r
    0.44
    POSITIVE LOGITS
     vicenda
    0.48
     کنی
    0.47
     kepentingan
    0.46
    ᓘ
    0.46
     referendum
    0.44
     vertreten
    0.43
     politische
    0.43
     satunya
    0.42
     adjoining
    0.42
     constitut
    0.42
    Act Density 0.023%

    No Known Activations