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

    Neuronpedia

    INDEX
    Explanations

    theme colors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ූ
    0.38
     LEWIS
    0.37
    備
    0.37
    вели
    0.37
     τότε
    0.36
    টিয়ে
    0.35
    inental
    0.35
    })}{\
    0.35
    χεία
    0.35
     नेटवर्क
    0.34
    POSITIVE LOGITS
    vim
    0.46
     Vim
    0.44
     vim
    0.43
     ವಿ
    0.40
     Gwyn
    0.40
     Guin
    0.40
    hig
    0.38
    녕
    0.38
     gu
    0.37
     separatist
    0.37
    Act Density 0.033%

    No Known Activations