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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lynch
    0.70
    તર
    0.67
     Medal
    0.58
    Provence
    0.57
     Hoff
    0.57
     Pedra
    0.56
     Phong
    0.56
    വിഡ്
    0.56
    tså
    0.56
     Division
    0.55
    POSITIVE LOGITS
    epers
    0.73
     পাকিস্তানের
    0.72
     sillons
    0.70
    工具
    0.70
    యిత
    0.69
     ನೀವು
    0.68
    ographical
    0.67
     circol
    0.66
    腈
    0.66
    omat
    0.65
    Act Density 0.000%

    No Known Activations