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

    Neuronpedia

    INDEX
    Explanations

    "largest possible ratio"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sever
    0.81
     kites
    0.77
     mics
    0.73
     labels
    0.73
    兼容
    0.72
     abbreviations
    0.72
     calendars
    0.72
    Airport
    0.70
    简称
    0.69
    th
    0.68
    POSITIVE LOGITS
    ítulo
    0.93
     Осно
    0.84
     Сло
    0.82
     подня
    0.81
     Teach
    0.79
    ﻲ
    0.79
     opleiding
    0.79
    ﻰ
    0.79
    assurer
    0.79
     мозга
    0.77
    Act Density 0.000%

    No Known Activations