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

    Neuronpedia

    INDEX
    Explanations

    student learning experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hormones
    0.46
     മാസ
    0.43
     childish
    0.43
     gangsters
    0.42
     celebs
    0.41
     girly
    0.40
     normals
    0.40
     fairies
    0.40
    odoris
    0.39
     کودک
    0.39
    POSITIVE LOGITS
     دانشج
    1.33
    学生
    1.32
     student
    1.30
    Students
    1.30
     Students
    1.29
     Student
    1.28
    學生
    1.28
    Student
    1.27
    students
    1.27
     students
    1.27
    Act Density 0.011%

    No Known Activations