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

    Neuronpedia

    INDEX
    Explanations

    academic integrity or ai writing homework

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ol
    0.38
    et
    0.37
     It
    0.36
     I
    0.36
     You
    0.36
    atet
    0.35
    ab
    0.34
     A
    0.33
    atan
    0.33
    bb
    0.33
    POSITIVE LOGITS
    ק
    0.55
    ق
    0.50
     heures
    0.49
    ミ
    0.47
     avaient
    0.45
    ی
    0.45
     muestras
    0.44
     enfri
    0.43
    าน
    0.43
     lửa
    0.43
    Act Density 0.000%

    No Known Activations