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

    Neuronpedia

    INDEX
    Explanations

    hardware (, variable, -)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ی
    0.94
    在
    0.92
    ف
    0.85
    ق
    0.83
     که
    0.78
     más
    0.73
    ใน
    0.73
     útil
    0.72
     indah
    0.71
    س
    0.71
    POSITIVE LOGITS
     Version
    0.62
     Tomcat
    0.61
     Supplies
    0.59
     Tom
    0.58
     Davies
    0.58
     Model
    0.57
     Phase
    0.57
     Williams
    0.57
     Clarke
    0.57
     Clark
    0.57
    Act Density 0.853%

    No Known Activations