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

    Neuronpedia

    INDEX
    Explanations

    D

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    èque
    0.74
    交代
    0.66
    abut
    0.66
    Integrating
    0.62
     লেখার
    0.62
    ත
    0.61
    ιχ
    0.61
     লিখতে
    0.61
    ফিক
    0.61
     shut
    0.60
    POSITIVE LOGITS
     PRO
    0.77
    ୫
    0.71
     Technol
    0.71
    verz
    0.70
    ocado
    0.69
    왁
    0.68
     Neat
    0.68
     হাড়
    0.67
    vär
    0.66
     சுண்ணா
    0.66
    Act Density 0.001%

    No Known Activations