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

    Neuronpedia

    INDEX
    Explanations

    specific topics and proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    یک
    0.59
    ﻬ
    0.56
    ן
    0.52
    ایید
    0.51
    ה
    0.51
    KA
    0.51
    2
    0.51
    ные
    0.50
    Gọi
    0.50
    কেই
    0.49
    POSITIVE LOGITS
     gripe
    0.59
     Piaget
    0.54
     కేంద్ర
    0.54
     Achievements
    0.53
    vann
    0.52
     Leipzig
    0.52
     Apex
    0.52
     AcOH
    0.51
     Thirteen
    0.51
     సాధారణ
    0.51
    Act Density 0.000%

    No Known Activations