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

    Neuronpedia

    INDEX
    Explanations

    grade levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     راجس
    0.40
     프로세
    0.38
     hydrodynamic
    0.38
     iterator
    0.38
    友
    0.38
     jagged
    0.37
     Bearded
    0.35
     Iterator
    0.35
     inodes
    0.35
     Runtime
    0.35
    POSITIVE LOGITS
     elementary
    1.39
     grade
    1.38
     undergraduate
    1.36
    高中
    1.32
    小学
    1.30
    Grade
    1.28
    小学生
    1.27
     Grade
    1.26
    中学
    1.26
     Elementary
    1.23
    Act Density 0.023%

    No Known Activations