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

    Neuronpedia

    INDEX
    Explanations

    teaching and guidance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hacker
    0.37
     negocios
    0.36
     financier
    0.36
    ubishi
    0.34
     iphdr
    0.34
     investor
    0.34
     hacking
    0.34
     marketer
    0.33
    <0x94>
    0.33
    libexec
    0.33
    POSITIVE LOGITS
     Teacher
    0.69
    Teacher
    0.68
     teacher
    0.63
     Classroom
    0.60
    Teaching
    0.60
     classroom
    0.60
     Teaching
    0.59
     worksheets
    0.58
     Teachers
    0.57
    教师
    0.56
    Act Density 0.108%

    No Known Activations