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

    Neuronpedia

    INDEX
    Explanations

    tkinter and ttk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻬ
    0.45
    breve
    0.45
    blica
    0.45
    㗁
    0.45
    ăl
    0.44
     frecuente
    0.44
    および
    0.44
    ﺿ
    0.43
    famous
    0.43
    ]]:
    0.43
    POSITIVE LOGITS
     verl
    0.51
     sein
    0.50
     sparkle
    0.50
     laut
    0.49
     Hersteller
    0.49
    ists
    0.49
     Nets
    0.48
     le
    0.48
     Enterprise
    0.47
     chests
    0.47
    Act Density 0.001%

    No Known Activations