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

    Neuronpedia

    INDEX
    Explanations

    acting as an instructor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    м
    1.03
    งาน
    1.02
    هاي
    1.02
     făcut
    0.99
    sthe
    0.99
    م
    0.99
    landı
    0.98
    Ꮅ
    0.97
    噦
    0.97
     हुए
    0.96
    POSITIVE LOGITS
    0
    1.52
    5
    1.51
    ill
    1.45
    3
    1.41
    s
    1.39
     instructors
    1.34
    4
    1.30
    instructor
    1.28
    '
    1.27
    6
    1.21
    Act Density 0.004%

    No Known Activations